12 accepted papers
We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refreshable vision-language prefixes. In contrast to existing Vision-Language-Action (VLA) models and diffusion policies that reset temporal context with each new ob…
A central challenge of visual control with model-based reinforcement learning (RL) is reliable long-horizon planning: Long rollouts with learned latent dynamics exhibit branching futures and multi-modal action-value distributions. In addition, compounding model error amplified by visual occlusions m…
We present a method that reduces, by an order of magnitude, the time and memory needed to train multi-task vision-language robotic diffusion policies. This improvement arises from a previously underexplored distinction between action diffusion and the image diffusion techniques that inspired it: In
We present a method that reduces, by an order of magnitude, the time and memory needed to train multi-task vision-language robotic diffusion policies. This improvement arises from a previously underexplored distinction between action diffusion and the image diffusion techniques that inspired it: In …
Real-world applications of vision-based robot learning face two major challenges: extreme partial observability and effective simulation-to-reality (sim-to-real) transfer. This letter introduces a robust robot learning framework that enhances uncertainty awareness to address these challenges. We rei
This paper studies sand profile grading, a manipulation task to obtain a desired geometric curve in sand. Manipulating sand is challenging because like other amorphous materials, its properties are difficult to estimate and emergent effects such as collapses may occur which both influence the manipu
There are two dominant approaches in modern robot grasp planning: dense prediction and sampling-based methods. Dense prediction calculates viable grasps across the robot’s view but is limited to predicting one grasp per voxel. Sampling-based methods, on the other hand, encode multi-modal grasp distr…
We address the problem of (a) predicting the trajectory of an arm reaching motion, based on a few seconds of the motion’s onset, and (b) leveraging this predictor to facilitate shared-control manipulation tasks, by reducing the operator’s cognitive load through assistance in their anticipated direct…
We consider the problem of rover relocalization in the context of the notional Mars Sample Return campaign. In this campaign, a rover (R1) needs to be capable of autonomously navigating and localizing itself within an area of approximately 50 ×50 m using reference images collected years earlier by a
We present a task-oriented grasp model, that encodes grasps that are configurationally compatible with a given task. For instance, if the task is to pour liquid from a container, the model encodes grasps that leave the opening of the container unobstructed. The model consists of two independent agen…
We present a probabilistic model for joint representation of several sensory modalities and action parameters in a robotic grasping scenario. Our non-linear probabilistic latent variable model encodes relationships between grasp-related parameters, learns the importance of features, and expresses co…
We present a robotic agent that learns to derive object grasp stability from touch. The main contribution of our work is the use of a characterization of the shape of the part of the object that is enclosed by the gripper to condition the tactile-based stability model. As a result, the agent is able…