Reasoning vision-language-action (VLA) models pair physical control with natural-language rationales that supervisors can read to monitor embodied safety. Prior attacks on VLA reasoning corrupt the rationale itself and leave visible evidence in the text. We show that visual perturbations can instead alter the physical...
Zihao Feng, Qingzhao Zhang, Chunyu Xia et al.· 0 citations
The results suggest that bridging the lab-to-store gap is primarily a systems integration challenge rather than an architectural one: careful data design and targeted post-training can transform a policy that fails under naive fine-tuning into a competent real-world system using only a single GPU.
Roger Sala Sisó, Tiago Silvério, J. Sand et al.· arXiv.org· 0 citations
Bimanual robot systems substantially expand manipulation capabilities, but coordinating two arms introduces additional control complexity and failure modes that are not well captured by existing benchmarks. We introduce DuoBench, an extensible benchmarking framework for bimanual manipulation policies on the FR3 Duo pla...
Tobias J\"ulg, Seongjin Bien, Simon Hilber et al.· 0 citations
With the rapid advancement of underwater net-working and multi-agent coordination technologies, autonomous underwater vehicle (AUV) ad-hoc networks have emerged as a pivotal framework for executing complex maritime missions, such as multi-target tracking. However, traditional data-centricarchitectures struggle to maint...
Kai Tian, Jialun Wang, Chuan Lin et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Effective exoskeleton assistance requires co-adaptation: as the device alters joint dynamics, the user reorganizes neuromuscular coordination, creating a non-stationary learning problem. Most learning-based approaches do not explicitly account for the sequential nature of human motor adaptation, leading to training ins...
The prediction of 3D semantic occupancy enables autonomous vehicles (AVs) to perceive the fine-grained geometric and semantic scene structure for safe navigation and decision-making. Existing methods mainly rely on either voxel-based representations, which incur redundant computation over empty regions, or object-centr...
A novel semantics and policy dual-driven hybrid decision framework to tackle the challenge of continuous learning and joint decision in EI driving, which merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning for real-time policy optimization.
Long Zhang, Yu-Chen Xia, Bing-Qing Wei et al.· 0 citations
Learning-based planners are sensitive to the long-tailed distribution of driving data. Common maneuvers dominate datasets, while dangerous or rare scenarios are sparse. This imbalance can bias models toward the frequent cases and degrade performance on critical scenarios. To tackle this problem, we compare balancing st...
Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy methods such as Proximal Policy Optimization (PPO) remain underexplored. We diagnose that PPO in MTRL suffers from a previously overlooked issue: critic-side gradient ill...
Yuanpeng Li, Gefei Lin, Annie Qu et al.· 0 citations
Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer actions from visual transitions, but their representations often entangle the und...
Jisoo Kim, Chaehyun Kim, Junsu Kim et al.· 0 citations
Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a coding agent can take over the teleoperator's job. In our DataFarm, the agent receives a data request and one calibration episode of the robot...
Kewei Zhang, Juncheng Ma, Guodong Lv et al.· 0 citations
Robot foundation models have shown remarkable performance in robot control, yet adapting them to a new task still relies heavily on teleoperated demonstrations. Egocentric human videos offer a scalable substitute, but overlaying rendered robots on human videos or retargeting human poses into robot actions leaves signif...
Seung-Yong Lee, Suhyeok Jang, Minyoung Kim et al.· 0 citations
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. The post Offloaded inference for real-world physical AI robotics appeared first on Microsoft Research.
