While energy efficiency is a critical objective for legged-robot locomotion control, achieving low energy consumption while maintaining robust performance across different velocity ranges and terrain conditions remains a key challenge. This is particularly true for end-to-end RL policies, where gait generation, motion...
Ammar Issa, Anubhav Singh, Anton Tsaritsin et al.· 0 citations
Results show how rich fingertip sensing and expressive temporal models that capture the dynamics of touch can support learned grasping with multi-fingered hands without explicit contact or force modeling, providing a scalable data-driven path from tactile experience toward stable dexterous manipulation.
Ken Nakahara, Aleksei Buvailik, P. Kotov et al.· 0 citations
Navigation-aware loss (NAViLoss), a robust and uncertainty-aware objective function for learning-based AUV velocity estimation, is introduced, demonstrating the effectiveness of navigation-aware and uncertainty-adaptive loss design for robust learning-based underwater velocity estimation.
Arup Kumar Sahoo, Itzik Klein· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Latent actions supervise robot policies with action-like codes inferred from visual transitions, and their usefulness hinges on two questions: what a code keeps from a transition, and whether it still means the same thing when reused in a different initial state. The first is a tension in time: an endpoint difference d...
When diffusion policies were first introduced, they were expected to recover multi-modal action distributions. However, we find this expectation does not always hold, as diffusion policies often collapse to a single modality even when we guarantee the balance of dataset modalities and exact within-batch symmetry. Our a...
Xiao Zhang, Yuxin Chen, Zhixuan Liang et al.· 0 citations
Learning from demonstrations (LfD) provides a framework for inferring unknown constraints from locally optimal, constraint-satisfying expert behavior. Existing approaches largely fall into two paradigms, constrained inverse optimal control (CIOC) and inverse constrained reinforcement learning (ICRL). CIOC exploits opti...
Humanoid robots still struggle to plan contact-rich whole-body manipulation from egocentric RGB and proprioception. Workhorse learns such manipulation from robot-free human demonstrations. A visual planner predicts five-link targets: the poses of the torso, both wrists, and both feet. A reinforcement-learning whole-bod...
Song-Bo Hu, Qia-Yuan Liao, Yu-Feng Chi et al.· 1 citation
Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's center of mass and impose sustained loads across the upper body, challenging balance and command tracking. We present HULK, a whole-body control framework for forceful loco-m...
An Dang, Arturo Flores Alvarez, Yu-Ming Chen et al.· 0 citations
This work introduces the first robotic platform for closed-loop autonomous liquid droplet navigation on an open, unconfined surface using model-based reinforcement learning and extends reinforcement-learning manipulation from rigid microrobots to deformable soft-matter systems for next-generation SDLs.
This work introduces time as a new dimension of interpretability, coined as temporal interpretability, and demonstrates how temporal abstractions via action chunking improve it, by first introducing two novel policy gradient algorithms that incorporate action chunking.
Eisuke Hirota, Aarav G. Sane, R. Paleja· 0 citations
Offline MARL increasingly relies on generative policies to model multimodal joint behavior, typically by distilling a centralized teacher into decentralized one-step actors under the CTDE. We identify a failure mode at the teacher training stage: standard flow-based teachers pair noise with replay targets independently...
Sang-Min Lee, Youngju Na, Chan-Mi Lee 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.
