Robotics & Automation
Robotics & Automation news — Wednesday 30 September 2026
150 stories from 3 sources, every one in English. Each links to its publisher.
-
The Robot Report parent Arrowfly launches AI for Engineers platform, events for engineers navigating AI
The Robot Report
Arrowfly has launched AI for Engineers, a resource including news, events, and an advisory board. Source: Arrowfly Arrowfly, the parent company of The Robot Report , today launched AI for Engineers, a resource for engineers and technical…
-
The Robot Report parent Arrowfly launches AI for Engineers platform, events for engineers navigating AI
Robotics Business Review
Arrowfly has launched AI for Engineers, a resource including news, events, and an advisory board. Source: Arrowfly Arrowfly, the parent company of The Robot Report , today launched AI for Engineers, a resource for engineers and technical…
-
Innodata opens motion-capture lab to help humanoids move more like people
Robotics Business Review
Innodata has opened a new lab to capture motion for accurate data to train AI for robotics. Source: Innodata While humanoid robots can be agile, the artificial intelligence driving them needs more data to be able to conduct useful tasks…
-
Innodata opens motion-capture lab to help humanoids move more like people
The Robot Report
Innodata has opened a new lab to capture motion for accurate data to train AI for robotics. Source: Innodata While humanoid robots can be agile, the artificial intelligence driving them needs more data to be able to conduct useful tasks…
-
Tackling construction labor shortages: ASI and SoftBank partner on autonomous fleets
The Robot Report
Autonomous Solutions Inc., or ASI, and SoftBank Group Corp. last week announced a joint venture to commercialize brand-agnostic autonomous heavy equipment to address severe labor shortages and accelerate infrastructure projects worldwide…
-
Tackling construction labor shortages: ASI and SoftBank partner on autonomous fleets
Robotics Business Review
Autonomous Solutions Inc., or ASI, and SoftBank Group Corp. last week announced a joint venture to commercialize brand-agnostic autonomous heavy equipment to address severe labor shortages and accelerate infrastructure projects worldwide…
-
GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning
arXiv cs.RO (Robotics)
arXiv:2609.36056v1 Announce Type: cross Abstract: In urban low-altitude flight, buildings reshape ambient wind into spatially varying 3D flow, making unmanned aerial vehicle (UAV) energy depend on local wind exposure as well as path…
-
Passive-Dynamic-Walking-Inspired Dynamics Guidance for Energy-Efficient Humanoid Locomotion
arXiv cs.RO (Robotics)
arXiv:2609.35935v1 Announce Type: new Abstract: Learning energy-efficient humanoid locomotion requires discovering mechanically economical gait coordination, not merely reducing actuator effort. Reinforcement learning promotes efficiency…
-
In-Context Learning for Robots: Methods and Applications
arXiv cs.RO (Robotics)
arXiv:2609.36012v1 Announce Type: new Abstract: General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this process by…
-
Executor-aware Candidate Selection via a Feasibility Certificate
arXiv cs.RO (Robotics)
arXiv:2609.36597v1 Announce Type: new Abstract: Modular robotic systems often separate motion planning from a downstream executor that enforces state-dependent hard constraints. A candidate that is geometrically valid may therefore be…
-
Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
arXiv cs.RO (Robotics)
arXiv:2609.36808v1 Announce Type: new Abstract: Current embodied models do not respond to their own failures, although what just went wrong could inform a small adjustment on the next attempt, the kind of reflection behind the gains of…
-
iTeach: In the Wild Interactive Teaching for Failure-Driven Adaptation of Robot Perception
arXiv cs.RO (Robotics)
arXiv:2410.09072v5 Announce Type: replace Abstract: We present iTeach, a deployable system that lets any co-located human fix a robot's perception failures on the spot without expertise, a workstation, or offline retraining. The operator…
-
EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
arXiv cs.RO (Robotics)
arXiv:2605.21862v3 Announce Type: replace Abstract: Chunked vision-language-action (VLA) policies generate multi-step actions from one observation and typically re-observe after executing the action chunk. Earlier actions change the scene…
-
HACo: Learning Haptic Active Compliance for Force-Aware Dexterous Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.36596v1 Announce Type: new Abstract: Contact-rich dexterous manipulation requires policies that translate physical feedback into motion commands while regulating interaction loads across evolving multi-contact interactions. This…
-
TaRL: Learning General and Physical Rewards from Tactile Demonstrations
arXiv cs.RO (Robotics)
arXiv:2609.36785v1 Announce Type: new Abstract: Contact-rich manipulation requires robots to sequence precise contacts, maintain stable grasps, and apply directed forces. Reinforcement learning (RL) can acquire such behaviors…
-
NIDAR: NIR-Guided Intrinsic Decomposition for Scalable Scene-Agnostic LiDAR Intensity Reconstruction
arXiv cs.RO (Robotics)
arXiv:2609.36878v1 Announce Type: new Abstract: LiDAR return intensity provides complementary surface-response cues for robotic perception and state estimation, yet many simulation pipelines omit it or reproduce it using reconstruction…
-
BCNav: Bearing-Conditioned Depth Policies for Sound Source Navigation
arXiv cs.RO (Robotics)
arXiv:2609.37084v1 Announce Type: new Abstract: The ability to navigate toward sound sources extends a robot's reach beyond its visual field, enabling response to auditory events in unknown environments. To equip robots with this…
-
CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts
arXiv cs.RO (Robotics)
arXiv:2609.37150v1 Announce Type: new Abstract: VLAs combine pretrained vision-language representations with action generation to enable language-guided control across diverse tasks, becoming a mainstream paradigm in embodied intelligence…
-
Remember What You Did: Action-History Memory with Dual-Expert Denoising for Long-Horizon Vision-Language-Action Policies
arXiv cs.RO (Robotics)
arXiv:2609.37307v1 Announce Type: new Abstract: Vision-language-action (VLA) models have driven rapid progress in robotic manipulation, demonstrating strong fine-grained control and promising performance on long-horizon tasks. However…
-
Video2STL: Grounding VLM-Generated Temporal Specifications for Robot Learning
arXiv cs.RO (Robotics)
arXiv:2609.37519v1 Announce Type: new Abstract: Video-based policy learning is particularly promising, as it illustrates target behaviors without requiring action annotations or embodiment-matched demonstrations. A central challenge is…
-
Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control
arXiv cs.RO (Robotics)
arXiv:2609.37552v1 Announce Type: new Abstract: While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target positions or…
-
RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.37530v1 Announce Type: new Abstract: Vision-language-action (VLA) models typically operate on RGB images produced by a fixed camera image signal processor (ISP), leaving the imaging pipeline outside the learning and evaluation…
-
StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks
arXiv cs.RO (Robotics)
arXiv:2609.36352v1 Announce Type: cross Abstract: Vision-language-action (VLA) models perform well on shorter-horizon manipulation tasks but still struggle with long-horizon tasks that require multiple dependent manipulations from a single…
-
GlassFormer: Learning Real-time Glass Segmentation using Radar-Depth Fusion
arXiv cs.RO (Robotics)
arXiv:2609.36844v1 Announce Type: cross Abstract: Transparent surfaces are ubiquitous in built environments, yet they remain a persistent failure case for robotic perception. RGB cameras perceive the background behind glass rather than the…
-
Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark
arXiv cs.RO (Robotics)
arXiv:2609.37938v1 Announce Type: cross Abstract: Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video accuracy conflates…
-
Rethinking Representations for World-Action Modeling
arXiv cs.RO (Robotics)
arXiv:2609.38163v1 Announce Type: cross Abstract: World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this…
-
Learning On The Job: Zero-Shot Task Execution under Parametric Uncertainty via Trajectory-Parametrized Dual Control
arXiv cs.RO (Robotics)
arXiv:2510.20483v2 Announce Type: replace Abstract: Model-based control can achieve reliable task performance, but its effectiveness depends on the accuracy of the underlying model. Robots operating under model uncertainty must often adapt…
-
RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance
arXiv cs.RO (Robotics)
arXiv:2608.09853v2 Announce Type: replace Abstract: General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from large-scale heterogeneous corpora…
-
Human-in-the-Loop Geospatial Annotation for Rapid Dataset Construction in Field-Deployed UAV Systems
arXiv cs.RO (Robotics)
arXiv:2609.28767v3 Announce Type: replace Abstract: Real-world perception systems must adapt to changing environments, but manual image annotation cannot scale to field data volumes. We present BirdsEye, which shifts expert annotation from…
-
AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents
arXiv cs.RO (Robotics)
arXiv:2609.33299v2 Announce Type: replace Abstract: World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the consequences of candidate actions before…
-
Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies
arXiv cs.RO (Robotics)
arXiv:2609.35231v2 Announce Type: replace Abstract: We propose NUDGE (Nudge Update via Differentiable GEometry), a training-free obstacle-avoidance procedure that can be incorporated in any robot policy based on diffusion or flow matching…
-
Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication
arXiv cs.RO (Robotics)
arXiv:2609.34373v2 Announce Type: replace-cross Abstract: Rate-limited multi-agent teams raise three questions the emergent-communication literature has answered only empirically: what an optimal message should encode, what compression…
-
Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.38172v1 Announce Type: new Abstract: Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist robots. However, collecting diverse, high-quality…
-
FineART: Fine-grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.36416v1 Announce Type: new Abstract: Robots operating in real-world environments must execute complex, multi-step bimanual tasks over long horizons rather than single, isolated actions. Current manipulation datasets struggle to…
-
World4Scorer: Outcome-Grounded World Modeling for Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2609.36438v1 Announce Type: new Abstract: Autonomous driving requires choosing a safe and efficient plan as surrounding traffic evolves. Generate-and-select planners propose multiple trajectories and score them for execution, and…
-
EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.36575v1 Announce Type: new Abstract: Visuomotor policies for humanoid loco-manipulation must generalize across object poses and lighting from only a handful of demonstrations. 3D Diffusion Policy (DP3) conditions a…
-
RoboChrono: A Real Robot Benchmark for Streaming Task Understanding
arXiv cs.RO (Robotics)
arXiv:2609.36605v1 Announce Type: new Abstract: Understanding ongoing robot manipulation requires models to interpret visual observations in relation to interaction history and task progress. We introduce RoboChrono, a benchmark for…
-
Recovering the View: Benchmarking Physical Active Vision for Occlusion Recovery in Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.37292v1 Announce Type: new Abstract: Physical active vision allows robots to change their viewpoint when task-relevant observations become unreliable, yet existing manipulation benchmarks provide limited support for studying how…
-
Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning
arXiv cs.RO (Robotics)
arXiv:2609.37554v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as high-level planners in robot navigation, but their outputs may become unreliable when instructions are ambiguous, unsupported by the…
-
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
arXiv cs.RO (Robotics)
arXiv:2609.37810v1 Announce Type: new Abstract: Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose…
-
PhysWAM: Physically Consistent World Action Model for Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2609.37970v1 Announce Type: new Abstract: World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily impose a shared geometric constraint on…
-
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2607.06559v2 Announce Type: replace Abstract: Robotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure moves under interaction. We argue that…
-
PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball
arXiv cs.RO (Robotics)
arXiv:2607.28623v2 Announce Type: replace Abstract: We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed…
-
Unified Visual-Tactile-Action Modeling from Human Demonstrations for Dexterous Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.34182v2 Announce Type: replace Abstract: Dexterous manipulation requires tactile feedback. However, robot tactile demonstrations are difficult to scale,because dexterous-hand teleoperation provides limited tactile feedback to…
-
F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement
arXiv cs.RO (Robotics)
arXiv:2609.35575v2 Announce Type: replace Abstract: The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of expert demonstrations and their insufficient understanding of…
-
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
arXiv cs.RO (Robotics)
arXiv:2609.34981v2 Announce Type: replace-cross Abstract: World action models (WAMs) predict the future alongside actions during training. Due to the heavy computation cost of video denoising, whether the future must still be generated…
-
T$^2$Mem: Learning Test-Time Memory for Robotics
arXiv cs.RO (Robotics)
arXiv:2609.36720v1 Announce Type: new Abstract: Memory-dependent robotic manipulation requires policies to use information that is no longer available in the current observation. Retaining history alone is insufficient: memory must…
-
DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.37348v1 Announce Type: new Abstract: Learning robust manipulation policies for diverse, long-horizon tasks from limited demonstrations remains a fundamental challenge in robotics. We present DROM, a language-guided diffusion…
-
MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.37793v1 Announce Type: new Abstract: World-Action Models (WAMs) couple visual dynamics with action prediction, bringing the rich priors of pretrained video models to robotic manipulation. However, their multi-view interfaces…
-
Skill-Space Shooting for Autonomous Robot Policy Improvement
arXiv cs.RO (Robotics)
arXiv:2609.38178v1 Announce Type: new Abstract: Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this improvement to scale across tasks, it must…
-
EgoAlign: Bridging the Human-Humanoid Gap for Long-Range Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.38046v1 Announce Type: new Abstract: Egocentric human demonstrations offer an accessible source of task experience, but differences in body scale and controller response, together with missing robot states, limit their value as…
-
DQ-MPCC: Dual-Quaternion MPCC for Quadrotor Racing
arXiv cs.RO (Robotics)
arXiv:2609.36482v1 Announce Type: new Abstract: Quadrotor racing demands aggressive attitude and progress control while passing through every gate, and conventional quadrotor MPCC formulations state the prediction model in inertial…
-
DRHeC: Differentiable Rendering for Hand-Eye Calibration with RGB-Based Gradients
arXiv cs.RO (Robotics)
arXiv:2609.36779v1 Announce Type: new Abstract: Accurate hand-eye calibration is crucial for precision manipulation. Traditional methods rely on markers, with their precision dependent on marker accuracy and observability. In contrast…
-
From Sky to Soil: A Morphing Aerial-Ground Robot for Seed Deployment
arXiv cs.RO (Robotics)
arXiv:2609.37072v1 Announce Type: new Abstract: Aerial seed broadcasting can reach remote restoration sites, but provides limited control over seed placement within the soil. This paper presents a geometry-assisted, tri-functional morphing…
-
Adversarially Robust Geometric Safety Certificates for Nonholonomic Robots Against Maneuvering Obstacles
arXiv cs.RO (Robotics)
arXiv:2609.37126v1 Announce Type: new Abstract: Safe navigation against obstacles that can actively maneuver within bounded capabilities remains challenging: robust control barrier function methods typically treat obstacle actions as…
-
Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method
arXiv cs.RO (Robotics)
arXiv:2609.35965v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) has largely focused on a single agent following a single instruction, yet many real-world applications require teams of robots to tackle tasks beyond…
-
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2601.01762v4 Announce Type: replace Abstract: Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use…
-
DORA: Divergence-Oriented Data-Relay Algorithm for Partially Connected Robot Teams
arXiv cs.RO (Robotics)
arXiv:2609.36395v1 Announce Type: new Abstract: Teams of unmanned aerial vehicles (UAVs) deployed for search and monitoring missions frequently operate as partially connected networks, forcing each robot to trade off exploring the…
-
Comparing Utility of Inertial, Occupancy, Semantic, and Intent Information in Human Motion Prediction During Daily Tasks
arXiv cs.RO (Robotics)
arXiv:2609.37971v1 Announce Type: new Abstract: Accurate human motion prediction is crucial for robotic systems operating around people, particularly in complex indoor spaces. In this study, we assess the relative importance of different…
-
Action Chunking Proximal Policy Optimization with Feedback Correction
arXiv cs.RO (Robotics)
arXiv:2609.36250v1 Announce Type: cross Abstract: Action chunking provides temporal abstraction in reinforcement learning by selecting short action sequences instead of individual actions, but many existing approaches face two limitations…
-
RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers
arXiv cs.RO (Robotics)
arXiv:2609.34210v2 Announce Type: replace Abstract: Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in robotics. Existing robotics benchmarks, however, primarily focus on…
-
WorldLine: Action-Driven Visual Simulation for Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.38059v1 Announce Type: new Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a scalable foundation for visual simulators…
-
Test-Time Adaptation of Manipulation Policies Under Actuator Degradation
arXiv cs.RO (Robotics)
arXiv:2609.36182v1 Announce Type: new Abstract: Robot manipulation policies are usually trained under the assumption that a commanded action produces the same motion as it did during training even after hours of operation. Real hardware…
-
Design and Validation of an Antagonistic Tendon-Driven Dexterous Robotic Hand with Bidirectional Operation
arXiv cs.RO (Robotics)
arXiv:2609.36241v1 Announce Type: new Abstract: Dexterous robotic hands typically reproduce human hand morphology but inherit its one-sided grasping workspace, requiring wrist or arm reorientation to grasp from the opposite side. Existing…
-
Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control
arXiv cs.RO (Robotics)
arXiv:2609.36305v1 Announce Type: new Abstract: World models jointly learn latent representations and dynamics that predict how high-dimensional observations evolve under actions. In this work, we propose a JEPA-style world model in which…
-
ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning
arXiv cs.RO (Robotics)
arXiv:2609.36333v1 Announce Type: new Abstract: Latent world models rely on representation geometry for planning, yet regularizing the latent marginal alone does not determine the state-to-state relationships used for action selection. We…
-
Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks
arXiv cs.RO (Robotics)
arXiv:2609.36471v1 Announce Type: new Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction adds further inference overhead to already…
-
Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine Tuning
arXiv cs.RO (Robotics)
arXiv:2609.36588v1 Announce Type: new Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs are pretrained on large-scale…
-
Foundation-Model-Guided Topology-Aware Semantic Risk Fields for Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.36640v1 Announce Type: new Abstract: Robot motion planning in everyday environments must satisfy hard geometric constraints while accounting for context-dependent semantic risk. We present a foundation-model-guided…
-
Kinematic Nonlinear Spatio-Temporal Trajectory Warping for Contact-Rich Dexterous Manipulation Demonstrations
arXiv cs.RO (Robotics)
arXiv:2609.36676v1 Announce Type: new Abstract: We present a straightforward but effective method for repurposing existing contact-rich dexterous manipulation demonstrations. Starting from inputs of hand and object trajectories, our method…
-
Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback
arXiv cs.RO (Robotics)
arXiv:2609.36107v1 Announce Type: new Abstract: While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these policies to rapidly adapt during…
-
Predictive Safety Curricula for Robust Legged Locomotion
arXiv cs.RO (Robotics)
arXiv:2609.37070v1 Announce Type: new Abstract: Rare but consequential failures can persist in learned locomotion policies for legged robots even when average task performance is high, in part because standard curricula primarily adapt…
-
Multifunctional Locomotion Control of Multi-Jointed BURs with Swimming and gait Capabilities
arXiv cs.RO (Robotics)
arXiv:2609.37086v1 Announce Type: new Abstract: Multimodal biomimetic underwater robots (BURs) can conduct underwater tasks suitable for the environment. Combining the characteristics of aquatic organisms enables the swimming and…
-
ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2609.37871v1 Announce Type: new Abstract: Average performance on routine driving benchmarks does not establish planner reliability under rare, safety-critical hazards. We proposed ExceptionDrive, a counterfactual planning benchmark…
-
MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.38078v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited, and their reliance on specialized…
-
Manifold-Constrained MPPI: Real-Time Sampling-Based Control for Nonlinear Equality-Constrained Robotic Systems
arXiv cs.RO (Robotics)
arXiv:2605.24813v2 Announce Type: replace Abstract: Sampling-based model predictive control methods, such as Model Predictive Path Integral (MPPI), offer derivative-free optimization and robustness in complex robotic systems. However…
-
Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabulary
arXiv cs.RO (Robotics)
arXiv:2609.36426v1 Announce Type: new Abstract: A detector pretrained on a broad corpus is fine-tuned on a narrow domain, its in-domain accuracy improves, and it ships. We ask what happens meanwhile to its coverage of objects the…
-
LIBERO-MAX: Do Robot Policies Adapt When the World Changes?
arXiv cs.RO (Robotics)
arXiv:2609.36518v1 Announce Type: new Abstract: Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previous scene…
-
Trajectory-Level Mode Guidance for Controllable Diffusion-Based Multi-Robot Motion Planning
arXiv cs.RO (Robotics)
arXiv:2609.36530v1 Announce Type: new Abstract: Motion planning often admits multiple feasible solutions, making multimodal generation valuable, particularly for flexible multi-robot coordination. Diffusion models naturally learn such…
-
Reactive Real-Time Flow Policies via Asynchronous Distribution Alignment
arXiv cs.RO (Robotics)
arXiv:2609.36540v1 Announce Type: new Abstract: Generalist robot policies such as vision-language-action models (VLAs) have achieved remarkable generalization, but their inference delays can conflict with the demands of real-time control…
-
Riemannian Splat Regression Models for Learning Time Fields on Arbitrary Riemannian Manifolds
arXiv cs.RO (Robotics)
arXiv:2609.36561v1 Announce Type: new Abstract: Motion planning on arbitrary Riemannian manifolds is an important and difficult problem that frustrates typical planning methods for Euclidean spaces. In particular, motion planning methods…
-
ComManip: Overfitting Manipulation Policies to Comfortable Regions
arXiv cs.RO (Robotics)
arXiv:2609.36928v1 Announce Type: new Abstract: Training robot manipulation policies relies on costly robot demonstrations, making large-scale data collection impractical. Meanwhile, to improve policy generalization, existing approaches…
-
Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference
arXiv cs.RO (Robotics)
arXiv:2609.36967v1 Announce Type: new Abstract: Existing VLA pruning strategies primarily select individual visual tokens according to task-level semantic relevance, while overlooking the spatial information required for robotic…
-
Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead
arXiv cs.RO (Robotics)
arXiv:2609.37165v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models remain brittle under visual distribution shifts, often relying on spurious correlations tied to domain-specific factors rather than task-relevant…
-
Battery-Aware Reinforcement Learning for Aggressive Quadrotor Flight
arXiv cs.RO (Robotics)
arXiv:2609.37316v1 Announce Type: new Abstract: Agile flight tasks such as drone racing and pursuit-evasion require strong acceleration and precise turns, but the available thrust changes as the battery discharges and voltage drops under…
-
Encore: Few-Shot Agentic Discovery of Manipulation Strategies
arXiv cs.RO (Robotics)
arXiv:2609.37359v1 Announce Type: new Abstract: Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves out how to grasp, in what order to make…
-
Surgical Master Console Using General-Purpose Robot Arms and a Separable Articulated Distal Interface: Porcine In-Vivo Evaluation
arXiv cs.RO (Robotics)
arXiv:2609.37455v1 Announce Type: new Abstract: High-performance surgical master consoles offer intuitive articulated manipulation but are expensive and difficult to reproduce, while accessible commercial haptic devices lack built-in…
-
RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.37583v1 Announce Type: new Abstract: Vision-language models can coordinate long-horizon robot manipulation, yet successful task reasoning still depends on whether local physical interactions produce the intended effects. We…
-
Credit-Guided Policy Improvement for Test-time Adaptive Vision-Language Navigation
arXiv cs.RO (Robotics)
arXiv:2609.37591v1 Announce Type: new Abstract: Test-time adaptation for vision-language navigation (TTA-VLN) enables pretrained policies to adapt online to unseen environments using only test-time observations and interaction history…
-
BlenDAgger: Blended Shared Control for Interactive Imitation Learning
arXiv cs.RO (Robotics)
arXiv:2609.37599v1 Announce Type: new Abstract: Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose…
-
Recompositional Robotics: Cross-Domain, Open-set, and Lifelong Modularity Beyond Morphology
arXiv cs.RO (Robotics)
arXiv:2609.37734v1 Announce Type: new Abstract: Research in modular robotics has produced capable approaches allowing a robot's morphology to change online, with recent efforts also developing approaches to decide which morphology to…
-
Stein-based Optimization of Sampling Distributions in Model Predictive Path Integral Control
arXiv cs.RO (Robotics)
arXiv:2511.02015v3 Announce Type: replace Abstract: This paper introduces a method for Model Predictive Path Integral (MPPI) control that optimizes sample generation towards an optimal trajectory through Stein Variational Gradient Descent…
-
Temporal Cascading of Planning and Control for Quadrotor MPC
arXiv cs.RO (Robotics)
arXiv:2512.12427v4 Announce Type: replace Abstract: Many aerial tasks involving quadrotors demand both instant reactivity and long-horizon planning for obstacle avoidance, energy efficiency, or trajectory tracking. High-fidelity models…
-
Altered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy
arXiv cs.RO (Robotics)
arXiv:2603.12717v2 Announce Type: replace Abstract: Vision-language-action policies map camera images and natural-language instructions to a robot's motor actions. Some of these policies are designed to reason in text before acting…
-
ADMM-based Continuous Trajectory Optimization in Graphs of Convex Sets
arXiv cs.RO (Robotics)
arXiv:2603.11335v2 Announce Type: replace Abstract: This paper presents a numerical solver for computing continuous trajectories in non-convex environments. Our approach relies on a customized implementation of the Alternating Direction…
-
EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control
arXiv cs.RO (Robotics)
arXiv:2606.08495v2 Announce Type: replace Abstract: Humanoid robots require whole-body motions that adapt to scene context, task requirements, and user intent. Motion tracking reproduces specified trajectories, and humanoid…
-
Elastic ODYN: Differentiable Optimization for Infeasible Control and Learning in Robotics
arXiv cs.RO (Robotics)
arXiv:2606.16564v2 Announce Type: replace Abstract: Robotic systems routinely encounter conflicting objectives, modeling errors, and degenerate contact conditions that render quadratic programs (QPs) infeasible. Yet most optimization…
-
Monocular 3D Occupancy Perception for Robots on Sidewalks via Hybrid 2D-3D Learning
arXiv cs.RO (Robotics)
arXiv:2606.19122v2 Announce Type: replace Abstract: Sidewalks in the real world are crowded, cluttered, and less structured than roads, making 3D occupancy prediction a key ingredient for the safe navigation of mobile robots such as…
-
From Sketch Prior to Trajectories: A Mission-Oriented Coordinated Navigation Framework for Indoor UAV Swarm
arXiv cs.RO (Robotics)
arXiv:2607.11386v2 Announce Type: replace Abstract: UAV swarm for applications, such as indoor inspection, security patrol, and logistics delivery, are often mission-oriented rather than exploration-oriented. In these tasks, UAVs are…
-
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory
arXiv cs.RO (Robotics)
arXiv:2608.16889v2 Announce Type: replace Abstract: Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-language-action (VLA) and world-action models (WAMs) increasingly master individual…
-
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
arXiv cs.RO (Robotics)
arXiv:2609.15195v3 Announce Type: replace Abstract: Embodied navigation requires agents to ground instructions or object goals in spatial observations and translate plans into successful execution. As multimodal large language models…
-
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
arXiv cs.RO (Robotics)
arXiv:2609.20820v2 Announce Type: replace Abstract: Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and…
-
A Novel Path-Tracking Algorithm for Automated Tractor-Trailer Forward and Backward Maneuvers
arXiv cs.RO (Robotics)
arXiv:2609.21718v2 Announce Type: replace Abstract: Fully autonomous tractor--trailer systems are increasingly deployed in logistics, agriculture, and industrial environments, where precise and robust path-tracking capabilities are…
-
From Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking
arXiv cs.RO (Robotics)
arXiv:2609.24631v2 Announce Type: replace Abstract: Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics and collision constraints…
-
Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
arXiv cs.RO (Robotics)
arXiv:2609.29382v2 Announce Type: replace Abstract: Flow-matching Vision-Language-Action (VLA) models have emerged as a potential solution for generalist robot control, designed by combining a pretrained Vision-Language Model (VLM)…
-
Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning
arXiv cs.RO (Robotics)
arXiv:2609.33145v2 Announce Type: replace Abstract: Constructing action targets from measured robot motion is an established approach in imitation learning. Under interaction constraints, however, command-state discrepancy may reflect…
-
CST-WM: A Causally Structured World Model for Embodied Visual Tracking
arXiv cs.RO (Robotics)
arXiv:2609.06302v2 Announce Type: replace-cross Abstract: Embodied visual tracking requires a robot to choose actions that keep a moving target observable at a suitable distance, and to recover it after occlusion, out-of-view drift, or…
-
AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents
arXiv cs.RO (Robotics)
arXiv:2609.28973v3 Announce Type: replace Abstract: Physical changes or sensing errors can invalidate embodied agents' task-relevant beliefs. AquaMend compares re-probing, rollback, and supported continuation on a probe-belief-action graph…
-
SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation
arXiv cs.RO (Robotics)
arXiv:2609.36171v1 Announce Type: new Abstract: Large-scale demonstrations have driven unprecedented progress in robot learning, yet collecting robot data through teleoperation is expensive and difficult to scale to diverse environments…
-
KPI: A Promptable Kernel for Physical Interaction on Humanoids
arXiv cs.RO (Robotics)
arXiv:2609.36151v1 Announce Type: new Abstract: Humanoids now walk, balance and reach with remarkable generality: one whole-body tracking policy follows references from a human, or from an end-to-end policy. That generality travels in the…
-
EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.37181v1 Announce Type: new Abstract: Human demonstrations capture diverse scenes and rich whole-body skills without requiring robot teleoperation. Prior work on egocentric transfer has emphasized scene generalization in…
-
WayFinder: Hierarchical Visual-Language-Action for Zero-Shot Waypoint Generation and Low-Level Kinematic Control
arXiv cs.RO (Robotics)
arXiv:2609.37922v1 Announce Type: new Abstract: Visual Language Action (VLA) models offer unprecedented generalization for autonomous robots; however, their real-world deployment is frequently bottlenecked by unreliable execution and the…
-
CrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments
arXiv cs.RO (Robotics)
arXiv:2609.38087v1 Announce Type: new Abstract: Behavior Foundation Models (BFMs) give humanoids a promptable policy over a latent behavior space, enabling one single vector to represent a motion to imitate, a pose to reach, or a reward to…
-
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
arXiv cs.RO (Robotics)
arXiv:2609.38173v1 Announce Type: new Abstract: We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem itself…
-
Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows
arXiv cs.RO (Robotics)
arXiv:2609.36812v1 Announce Type: cross Abstract: Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behavior policy can discourage actions…
-
Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation
arXiv cs.RO (Robotics)
arXiv:2609.37398v1 Announce Type: cross Abstract: World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning paradigms typically improve behavior…
-
Soft yet Effective Robots via Holistic Co-Design
arXiv cs.RO (Robotics)
arXiv:2505.03761v2 Announce Type: replace Abstract: Soft robots promise inherent safety via their material compliance for seamless interactions with humans or delicate environments. Despite progress, the field struggles to balance…
-
Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think
arXiv cs.RO (Robotics)
arXiv:2609.30036v3 Announce Type: replace-cross Abstract: Latent world models plan toward goal images with a frozen pretrained predictor, without task rewards or extra trained heads. However, their planners struggle with long-range goals…
-
ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2609.37131v1 Announce Type: new Abstract: Human-in-the-loop reinforcement learning (HIL-RL) offers a promising route to efficient training of robotic manipulation policies by combining autonomous learning with human demonstrations…
-
Towards Spatial Perception for Heterogeneous Robot Collaboration in Subterranean Mining Environments
arXiv cs.RO (Robotics)
arXiv:2609.37419v1 Announce Type: new Abstract: The autonomous extraction of deep mineral deposits in abandoned underground mines is fundamentally a multi-agent integration problem. No single platform simultaneously offers the mobility to…
-
FORM: Robot Manipulation through Direct Material Law Identification
arXiv cs.RO (Robotics)
arXiv:2609.38105v1 Announce Type: new Abstract: When interacting with an unfamiliar deformable material, a robot lacks prior knowledge of its physical properties and how it will respond to applied forces and motion. Rapid online…
-
EVO-WAM: Evolving World Action Models through Video-Action Verification
arXiv cs.RO (Robotics)
arXiv:2609.38057v1 Announce Type: cross Abstract: Improving robot policies on new tasks without collecting additional expert demonstrations remains a central challenge in robot learning. World action models (WAMs) use broad video priors to…
-
A Disk-Shaped Magnetoelastic Torque Sensor for Robotic Joints Using Permanent Magnetization
arXiv cs.RO (Robotics)
arXiv:2609.33542v2 Announce Type: replace Abstract: Direct torque sensing is a growing need in the robotics community to enable precise control and interactions where torque estimation from motor current is not sufficient. This paper…
-
RoboFin3D: A Sim-to-Real Platform for Robotic Surface Finishing
arXiv cs.RO (Robotics)
arXiv:2609.37560v1 Announce Type: new Abstract: Grinding and sanding are fundamental processes in industrial robotic surface finishing. However, physical trials are expensive and consume workpieces, making reproducible experiments…
-
Cascaded consensus splitting for multi-branch contingency games
arXiv cs.RO (Robotics)
arXiv:2609.37612v1 Announce Type: new Abstract: Contingency games enable agents to anticipate and plan for other agents' hypothetical intents by constructing trajectories with a shared prefix and intent-dependent branches. While…
-
CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfaces
arXiv cs.RO (Robotics)
arXiv:2609.37721v1 Announce Type: new Abstract: Robot policies increasingly incorporate semantic reasoning and future-world prediction, yet combining these capabilities does not guarantee that local predictions and actions remain aligned…
-
Rho: A Foundation for Efficiently Adaptable VLA Models
arXiv cs.RO (Robotics)
arXiv:2609.38164v1 Announce Type: new Abstract: General-purpose physical AI models must combine broad visual and linguistic capabilities with precise control across robot embodiments and efficient adaptation to downstream tasks. We…
-
Hyper Yoshimura: How a slight tweak on a classical folding pattern unleashes meta-stability for deployable robots
arXiv cs.RO (Robotics)
arXiv:2505.09919v3 Announce Type: replace Abstract: Deployable structures inspired by origami have provided lightweight, compact, and reconfigurable solutions for various robotic and architectural applications. However, creating an…
-
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
arXiv cs.RO (Robotics)
arXiv:2607.06558v3 Announce Type: replace Abstract: Scaling robot learning requires massive, diverse trajectory data, yet collection is currently bottlenecked by physical teleoperation, where every demonstration binds operator time to…
-
Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation
arXiv cs.RO (Robotics)
arXiv:2609.32292v2 Announce Type: replace Abstract: Vision-and-language navigation increasingly relies on general-purpose semantic planners, yet translating correct high-level intent into reliable physical execution remains difficult in…
-
FACT: Fidelity-Aware Construction of Articulated Twins
arXiv cs.RO (Robotics)
arXiv:2609.37067v1 Announce Type: new Abstract: Visually plausible articulated assets may still fail during contact interactions or exhibit inaccurate motion. We present FACT (Fidelity-Aware Construction of Articulated Twins), an agentic…
-
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
arXiv cs.RO (Robotics)
arXiv:2609.37334v1 Announce Type: new Abstract: Vision-language-action (VLA) policies often fail when a robot's executed motion deviates from their commanded action. Such execution errors arise from the robot's mechanics and operating…
-
Degeneracy-Orthogonal Geometric Constraints for LiDAR SLAM
arXiv cs.RO (Robotics)
arXiv:2609.36753v1 Announce Type: new Abstract: Autonomous robot navigation relies on simultaneous localization and mapping (SLAM) to estimate motion and maintain an accurate pose within an environment. However, in axially uniform…
-
S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information
arXiv cs.RO (Robotics)
arXiv:2607.26047v2 Announce Type: replace Abstract: Acoustic information provides rich cues about object location, material properties, and changes caused by contact or motion. This paper introduces a new set of acoustic-aware manipulation…
-
Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video
arXiv cs.RO (Robotics)
arXiv:2609.36924v1 Announce Type: new Abstract: Learning humanoid skills from videos typically requires a successful human demonstration, which often demands custom data collection. Although failures have traditionally been treated only as…
-
A robust single-sensing-element tactile sensor for concurrent pressure and tackiness detection with real-time signal decoupling capability
arXiv cs.RO (Robotics)
arXiv:2609.36558v1 Announce Type: new Abstract: Integrating tackiness sensation into the artificial skin of humanoid robots significantly enhances their cognitive and operational capabilities. However existing tactile sensors face…
-
OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport
arXiv cs.RO (Robotics)
arXiv:2609.36602v1 Announce Type: new Abstract: Transferring human motion to humanoid robots requires adapting the demonstrated motion to the robot morphology while preserving interactions with the environment. This is particularly…
-
ProAct-VLM: Pre-Failure Vision-Language Task Replanning with Continuous Perception Feedback
arXiv cs.RO (Robotics)
arXiv:2609.37681v1 Announce Type: new Abstract: Long-horizon robotic tasks are vulnerable to unexpected environmental changes that can render planned actions ineffective or unsafe. To address this, robots must detect such changes as they…
-
Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Acceleration
arXiv cs.RO (Robotics)
arXiv:2609.37771v1 Announce Type: new Abstract: Simulated manipulation benchmarks are the standard tool for evaluating vision-language-action (VLA) policies and the acceleration methods that reduce their inference latency for on-robot…
-
A QCQP-Representable IMU Pre-Integration Factor for Certifiable State Estimation
arXiv cs.RO (Robotics)
arXiv:2609.38048v1 Announce Type: new Abstract: We propose a QCQP-representable IMU pre-integration factor that enables certifiable estimation with pre-integrated inertial measurements. To the best of our knowledge, this is the first work…
-
AGRO-SUVIDE: Agentic Robotics for Surgical Viscoelastic Debridement
arXiv cs.RO (Robotics)
arXiv:2609.34823v2 Announce Type: replace Abstract: Augmented dexterity has the potential to reduce the fatigue experienced by surgeons during repetitive surgical tasks. In this paper, we propose the first AGentic RObotics framework for…
-
Receding-Horizon Pushing with Composable Object-Centric Policies
arXiv cs.RO (Robotics)
arXiv:2609.23439v2 Announce Type: replace Abstract: Non-prehensile manipulation is practical for relocating large, heavy, or geometrically ungraspable objects. Yet, long-horizon pushing of arbitrarily-shaped 3D objects couples three…
-
All You Need Is Low Fidelity: Zero-Shot Sim-to-Real of Learned Robotic Fish Control
arXiv cs.RO (Robotics)
arXiv:2609.36993v1 Announce Type: new Abstract: Complex tasks for underwater robots remain limited by the capabilities of their controllers. Learning a better one for a soft, underactuated robotic fish trades simulator cost against…
-
RobotValues: Evaluating Household Robots When Human Values Conflict
arXiv cs.RO (Robotics)
arXiv:2606.03312v2 Announce Type: replace Abstract: While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations where robots are expected to choose actions that…
-
Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models
arXiv cs.RO (Robotics)
arXiv:2609.37297v1 Announce Type: cross Abstract: Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet a target motion that shows the right action has two…
-
When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation
arXiv cs.RO (Robotics)
arXiv:2609.37602v1 Announce Type: new Abstract: Robust and reliable perception is essential for autonomous robots operating in real-world environments, particularly in long-term missions where environmental conditions may change…
-
Contact-Adaptive Robotic Ultrasound Probe Control for Tissue Exploration and Continuous Task-Relevant Visualization Using Robot-Free Image-Motion Demonstration
arXiv cs.RO (Robotics)
arXiv:2609.37456v1 Announce Type: new Abstract: Robotic ultrasound commonly targets standardized views, predefined scanning protocols, or expert-scan reproduction. We target a different role: while a clinician performs the primary…
-
Temporal Self-Imitation Learning
arXiv cs.RO (Robotics)
arXiv:2606.19752v3 Announce Type: replace Abstract: Long-horizon policies trained with reinforcement learning can still achieve high return through inefficient interactions, while rare efficient behaviors discovered during training may be…
-
doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2609.38028v1 Announce Type: new Abstract: Autonomous vehicles interacting with passengers through natural language must reason beyond immediate commands. Passenger intent may span multiple stages of behavior, depend on future events…
-
ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2609.36238v1 Announce Type: cross Abstract: A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Yet, critics in contrastive and…