Haptic interactions, such as touching an object in virtual reality, involve detecting a plethora of sensations through the skin. Whilst tactile displays exist to simulate and manipulate all of these cues individually, little progress has been made constructing devices that can control multiple cues simultaneously. This...
Joshua Brown, Fernando Bello, L. Jones· EuroHaptics· 1 citation
VREgo trains manipulation policies from demonstrations recorded on consumer VR headsets with EgoKit with EgoKit on one such headset, the PICO 4 Ultra, and adapts HumanEgo's preprocessing to estimate grasp thresholds per recording, update object positions after release, and propagate segmentation masks between keyframes...
Pedestrians increasingly encounter robots in urban public spaces without interacting with them, but how robots change the perceived safety of a street remains unclear. We examine how robot presence and type affect perceived safety across urban contexts. We generate 18 images of Seoul streets that vary in time of day, r...
Keonhee Jang, Kanghoon Lee, Seokwoo Yun et al.· 0 citations
Short-horizon model predictive control (MPC) is fast but myopic. ZipMPC compensates by learning a context-dependent correction of the short-horizon cost that imitates a long-horizon expert. We observe that the optimal correction is often multimodal: when a slower opponent can be passed on either side, good corrections...
Ke Zhang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly employ expert-agent switching systems to reduce the expert's burden by limitedly selecting the supervision timing. However, this approach is useful only for static tasks; in dynami...
Despite the numerous applications of convex constraints in Robotics, enforcing them within learning-based frameworks remains an open challenge. Existing techniques either fail to guarantee satisfaction at all times, or incur prohibitive computational costs. This paper presents RAYEN, a framework for imposing hard conve...
Jesus Tordesillas, Victor Klemm, Jonathan P. How et al.· 0 citations
Humanoid robots are typically trained as solitary agents, leaving them unable to coordinate physically with human partners who naturally anticipate and adjust to one another. To bridge this gap, we present Social Humanoid, a hierarchical system that generates and executes socially responsive whole-body motion on a 29-D...
Vongani H. Maluleke, James Ni, Kie Horiuchi et al.· 0 citations
This work proposes Stability-Hybrid On-Policy Reinforcement Learning (SHORE), which combines a learned stability probability of a placement with an on-policy estimate of its return conditional on stability, and shows faster learning and higher utilization on the more demanding realistic box arrival set.
Background and Objective: Our main goal is ultrasound guidance: moving a probe until its image matches a target view. Published methods for each part of a guide are evaluated in separate simulators. We asked whether these methods, combined into one guide, are good enough.
Methods: We built USB Gym, a testbed whose st...
Thanapong Intharah, Zhichao Gao, Yiliang Liu et al.· 0 citations
A personalizable transformer-based model mapping individuals'muscle activations to prescribed contact force trajectories when interacting with an end-effector rehabilitation robot to establish a foundation for future validation in clinical populations and provide a proof of concept for data-driven, activation-targeted...
Gabriel Parra, Kimia Khoshnami, Daniel S. Brown et al.· 0 citations
It is shown that JEPA features outperform video VAE latents, most clearly out of distribution, and that training-time future prediction choices significantly impact the policy even when future prediction is skipped at inference, suggesting that robot foundation models may benefit from architectures designed for control...
Mateo Clémente, George Z. Xue, Amin Abyaneh et al.· 0 citations
Robot reinforcement learning increasingly runs environments outside the trainer: in another process, on another machine, in another language. Many faults at this boundary raise no error. We make the boundary a wire protocol and ask what notices a fault in it.
On Pendulum, HalfCheetah, Hopper and a 7-joint arm (Pusher...
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.
