arXiv:2611.12983v1 Announce Type: new Abstract: Scene-driven robot autonomy requires selecting tasks from observations as well as executing them. We study scene-driven…
arXiv:2610.30671v1 Announce Type: new Abstract: Visual Language Action (VLA) models are designed to be generalist robot models that can be implemented across…
arXiv:2611.17566v1 Announce Type: new Abstract: Safety in robotics does not solely depend on geometric constraints, but also on semantics: the given task, environment…
arXiv:2611.23926v1 Announce Type: new Abstract: Vision-language-action (VLA) models generate local actions from visual observations, language, and robot state, but…
arXiv:2611.19274v1 Announce Type: new Abstract: Long-horizon embodied tasks fail in ways that end-task success cannot see. HospitalBench is a diagnostic benchmark of ten…
arXiv:2611.25320v1 Announce Type: cross Abstract: Residual reinforcement learning corrects an imitation-trained base policy using a limited budget of environment…
arXiv:2611.23858v1 Announce Type: new Abstract: Grasping is a fundamental capability for robotic manipulation, with the appropriate grasp depending on the downstream…
arXiv:2611.17631v1 Announce Type: new Abstract: Visuomotor imitation learning has become a predominant paradigm for real-world robotic manipulation, yet it remains…
arXiv:2611.25254v1 Announce Type: new Abstract: Autonomous robots may need to adapt both their task plans and architectural configurations as operating conditions…
arXiv:2611.13344v1 Announce Type: new Abstract: Task-driven design of soft robots requires the consideration of factors such as geometry, morphology, material…
arXiv:2610.33487v1 Announce Type: new Abstract: Robots can use historical observations to answer spatiotemporal queries in familiar environments, but the presence of…
arXiv:2611.18702v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies are vulnerable to adversarial visual perturbations, while defenses often require…
arXiv:2610.36694v1 Announce Type: new Abstract: Flow-based policies for language-conditioned multi-task manipulation commonly share a single $\textit{Gaussian}$ source…
arXiv:2610.40748v1 Announce Type: new Abstract: Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot…