By Topic:
By Type:
To truly understand how children envision a robot-integrated future, we used personal photo probes and a scaffolded design process to first uncover the values and...
Automatically converting demos into labeled datasets to enable the rapid training of task-specific object detectors that outperform existing state-of-the-art VLMs.
We propose two improvements to Residual RL that further enhance its sample efficiency and make it suitable for stochastic base policies. First, we leverage uncertainty...
We introduce real-is-sim, a new approach to integrating simulation into behavior cloning pipelines. In contrast to real-only methods, our framework allows policies to seamlessly switch...
We’ll be presenting robotic research that includes contact-rich bimanual manipulation and policy learning, an open source package for sample-based Model Predictive Control (MPC), how to...
AthenaZero can juggle barehanded using onboard vision feedback. By using multi-fingered hands, it can transition seamlessly between a wide range of juggling patterns.
We propose Q2RL, Q-Estimation and Q-Gating from Behavior Cloning for Reinforcement Learning, an algorithm for efficient offline-to-online learning.
We introduce a multi-task RL training paradigm that treats reference motion as a prior for behavioral shaping rather than a deployment-time constraint.
How AnyTask and ExpertGen Bridge the Sim-to-Real Gap
To make sure the data collected transfers to the robot, we’ve co-designed handheld and robot grippers: same linkage mechanisms, same degrees of freedom, same force...
Redesigning how we collect bespoke data for manipulation tasks.
We propose a framework to help the robotics community explore how automation impacts jobs that are considered dull, dirty, dangerous (DDD).
