Michael Equi

Training-Time Action Conditioning for Efficient Real-Time Chunking

Kevin Black, Allen Z. Ren, Michael Equi, Sergey Levine

Real-time chunking (RTC) enables vision-language-action models (VLAs) to generate smooth, reactive robot trajectories by asynchronously predicting action chunks and conditioning on previously committed actions via inference-time inpainting. However, this inpainting method introduces computational overhead that increases inference latency. In this work, we …

$π^{*}_{0.6}$: a VLA That Learns From Experience

Physical Intelligence, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black et autres

We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates …

π₀: A Vision-Language-Action Flow Model for General Robot Control

Kevin Black, Noah Brown, Danny Driess, A. Esmail et autres

&&0'% ) 8::!7 2/ .()/) 'GG) Z)0./GSO/,SGL ./O/), G m l hg/%('(G0 /)S/,G% y&/%,)p.n 2.G .G,)|{z 0 /) G2G.G.G 0%G) 2.G .(°2G)©¯SO/,SG )¡ G ,)S³)S/.G± O') O%G 20 )O/ %G O()(./0G.G /2G)2/20/.%/,),pG /. )%G(/ S G)0/&&GG ÀGG2) O%G GS2 ³),.³G.G ) O%G …

us (code pays fourni par la source)

$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Physical Intelligence, Kevin Black, Noah Brown, James Darpinian et autres

In order for robots to be useful, they must perform practically relevant tasks in the real world, outside of the lab. While vision-language-action (VLA) models have demonstrated impressive results for end-to-end robot control, it remains an open question how far such models …

Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models

Lucy Xiaoyang Shi, Brian Ichter, Michael Equi, Liyiming Ke et autres

Generalist robots that can perform a range of different tasks in open-world settings must be able to not only reason about the steps needed to accomplish their goals, but also process complex instructions, prompts, and even feedback during task execution. Intricate instructions …

$π_0$: A Vision-Language-Action Flow Model for General Robot Control

Noah Brown, Danny Driess, A. Esmail, Michael Equi et autres

Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the level of generality required for effective …

Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning

Dhruv Shah, Michael Equi, Błażej Osiński, Fei Xia et autres

Navigation in unfamiliar environments presents a major challenge for robots: while mapping and planning techniques can be used to build up a representation of the world, quickly discovering a path to a desired goal in unfamiliar settings with such methods often requires …

Multiple UAVs on a shared tether: Use cases, modeling, and probabilistic path planning

James Humann, Michael Equi, Natalie Link, Perla Latorre-Suárez

We analyze the concept of multiple unmanned aerial vehicles (UAVs) on a shared tether (MUST), where the UAVs act as control nodes for the shape of the tether, enabling the system to maneuver around obstacles without tangling or colliding for increased flexibility …

us (code pays fourni par la source)