6 papers · 1 filter
SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibration
Harshitha Rajaprakash, Aditeya Prajapati, Rong Xue +2
Vision-language-action policies often fail under deployment-time distribution shifts such as clutter, distractor objects, lighting changes, novel objects, altered initial states, a…
Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
Chancharik Mitra, Yusen Luo, Raj Saravanan +7
Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for…
RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning
Rohan Gupta, Trevor Asbery, Zain Merchant +2
Coordinating heterogeneous robot fleets to achieve multiple goals is challenging in multi-robot systems. We introduce an open-source and extensible framework for centralized multi-…
ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
Jiahui Zhang, Yusen Luo, Abrar Anwar +5
We introduce ReWiND, a framework for learning robot manipulation tasks solely from language instructions without per-task demonstrations. Standard reinforcement learning (RL) and i…
Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection
Abrar Anwar, Rohan Gupta, Zain Merchant +3
Evaluating learned robot control policies to determine their physical task-level capabilities costs experimenter time and effort. The growing number of policies and tasks exacerbat…
Contrast Sets for Evaluating Language-Guided Robot Policies
Abrar Anwar, Rohan Gupta, Jesse Thomason
Robot evaluations in language-guided, real world settings are time-consuming and often sample only a small space of potential instructions across complex scenes. In this work, we i…