Search for: All records

Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots. We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9 m/s. This system runs and turns fast on natural terrains like grass, ice, and gravel and responds robustly to disturbances. Our controller is a neural network trained in simulation via reinforcement learning and transferred to the real world. The two key components are (i) an adaptive curriculum on velocity commands and (ii) an online system identification strategy for sim-to-real transfer. Videos of the robot’s behaviors are available at https://agility.csail.mit.edu/ .

 

A robot’s deployment environment often involves perceptual changes that differ from what it has experienced during training. Standard practices such as data augmentation attempt to bridge this gap by augmenting source images in an effort to extend the support of the training distribution to better cover what the agent might experience at test time. In many cases, however, it is impossible to know test-time distribution- shift a priori, making these schemes infeasible. In this paper, we introduce a general approach, called Invariance through Latent Alignment (ILA), that improves the test-time performance of a visuomotor control policy in deployment environments with unknown perceptual variations. ILA performs unsupervised adaptation at deployment-time by matching the distribution of latent features on the target domain to the agent’s prior experience, without relying on paired data. Although simple, we show that this idea leads to surprising improvements on a variety of challenging adaptation scenarios, including changes in lighting conditions, the content in the scene, and camera poses. We present results on calibrated control benchmarks in simulation—the distractor control suite—and a physical robot under a sim-to-real setup. Video and code available at: https: //invariance-through-latent-alignment.github.io 

Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features. To mitigate this prob- lem, we propose learning Task Informed Ab- stractions (TIA) that explicitly separates reward- correlated visual features from distractors. For learning TIA, we introduce the formalism of Task Informed MDP (TiMDP) that is realized by train- ing two models that learn visual features via coop- erative reconstruction, but one model is adversari- ally dissociated from the reward signal. Empirical evaluation shows that TIA leads to significant per- formance gains over state-of-the-art methods on many visual control tasks where natural and un- constrained visual distractions pose a formidable challenge. Project page: https://xiangfu.co/tia