Robots in shared settings may expose information intended for an individual user to nearby bystanders. Robot tutoring makes this concern particularly salient: critical feedback is directed at an individual learner, yet bystanders may overhear or see it. To address this, we compared context-invariant and context-adaptiv...
Atikkhan Faridkhan Nilgar, Manuel Dietrich, Kristof Van Laerhoven· 0 citations
In shared settings, social robots may need to exchange information with an individual while limiting co-present others' access to or interpretation of that information. Publicly observable speech and gestures may not adequately support such exchanges. We investigate a wearable-mediated channel for discreet interaction...
Atikkhan Faridkhan Nilgar, Manuel Dietrich, Kristof Van Laerhoven· 0 citations
Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trained for static recognition or vision-language alignment, leaving motion understanding to downstream policies. We introduce DynaFLIP, a dynam...
Jusuk Lee, Seungjae Lee, Jonghun Shin et al.· 0 citations
A dexterous hand succeeds or fails through contact, yet every scalable record of human manipulation (video, vision-based hand tracking, motion capture) observes how the hand moves and misses how it pushes. We present DexCanvas, a hybrid real-synthetic dataset of 7,000 hours of dexterous hand-object interaction with per...
Xinyue Xu (Daisy), Jieqiang Sun (Daisy), Jing (Daisy) et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Inverse kinematics (IK) converts end-effector pose commands into joint motion, and many vision-language-action (VLA) policies rely on it to act on a given arm and to transfer across embodiments. Precise IK remains laborious: redundancy and singularities complicate the inverse mapping, execution depends on hand-tuned co...
Yuhan Liu, Xinqi Liu, Zixuan Dong et al.· 0 citations
Imitation learning policies in robotics are trained on datasets collected through costly real-world teleoperation. Often, the data-collection process is unguided, relying on the teleoperator's intuition, resulting in data that contributes little to overall policy performance. Recent work has shown that curating such un...
Shivin Dass, Kevin Nguyen, Rohan Yelandur et al.· 0 citations
Regularizing online reinforcement learning (RL) toward a pretrained base policy can improve sample efficiency and learning stability, but regularization that is too restrictive limits how much the policy can improve. Base policies -- typically diffusion or flow-matching models trained by imitation learning on large, di...
Charles Xu, Jacob Berg, Liyiming Ke et al.· 0 citations
It is shown that naively fine-tuning pre-trained policies fails in non-episodic settings due to shifts in object configurations and end-effector poses; however, these challenges can be mitigated through targeted reset allocation and by addressing biases in pre-trained models.
3D World Simulator is introduced, an action-conditioned multimodal world modeling framework that jointly predicts appearance, geometry, and tactile observations from a unified 3D representation that enables scalable data generation for policy training and evaluation using tactile and multi-view visual observations.
Ji-Chuan Wang, Yi-Fan Chou, Kai-Feng Zhang et al.· 0 citations
Vision-Language-Action (VLA) models generalize across tasks, but their autoregressive decoders need sequential forward passes in proportion to the action horizon, each bounded below on embedded aerial platforms by streaming billions of parameters from memory. We present Aero-VPA, a lightweight Vision-Predictor-Action a...
Visuomotor policies trained via behavior cloning are vulnerable to covariate shift, where small deviations from expert trajectories can compound into failure. Common strategies to mitigate this issue involve expanding the training distribution through human-in-the-loop corrections or synthetic data augmentation. Howeve...
Continual learning in physical AI differs from conventional continual learning because small per-step policy errors can accumulate over a trajectory. Each deviation may move the agent outside the training distribution, increase subsequent prediction errors, and ultimately cause closed-loop task failure. This work intro...
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.
