Meta tags:
author= Huang (Raven) Huang;
Headings (most frequently used words):
-
Text of the page (most frequently used words):
the (16), huang (16), for (11), and (11), robot (8), tactile (8), ken (7), goldberg (7), learning (7), real (5), self (5), supervised (5), vision (5), equal (4), contribution (4), your (4), browser (4), does (4), not (4), support (4), video (4), tag (4), nerf (4), locomotion (4), context (4), jeffrey (3), ichnowski (3), collect (3), planar (3), casting (3), data (3), with (3), letian (3), grasping (3), touch (3), 2024 (3), legged (3), that (3), website (3), language (3), task (3), prof (3), lawrence (2), yunliang (2), chen (2), way (2), then (2), learn (2), from (2), paper (2), icra (2), dynamic (2), actions (2), justin (2), kerr (2), propose (2), evo (2), additional (2), train (2), oral (2), presentation (2), roberto (2), calandra (2), representation (2), contrastive (2), active (2), perception (2), tasks (2), arm (2), asset (2), beyond (2), control (2), how (2), manipulator (2), gaurav (2), datta (2), william (2), chung (2), panitch (2), dataset (2), observations (2), human (2), alignment (2), next (2), token (2), prediction (2), imitation (2), transformer (2), arxiv (2), nbsp (2), advised (2), fei (2), raven (2), vincent, lim, jonathan, wang, daniel, seita, michael, laskey, 2021, tune, simulation, isaac, gym, more, tuned, simulator, combined, upsampled, policy, reach, given, target, attaining, median, error, distance, cable, length, ranging, real2sim2real, physical, single, step, yahav, avigal, matthew, tancik, angjoo, kanazawa, 2022, geometry, regularizations, improving, performance, rapid, capture, settings, achieve, time, updateable, scene, reconstruction, rapidly, table, top, transparent, objects, adapted, network, learns, ignore, floaters, openreview, corl, evolving, sequential, albert, wilcox, ryan, hoque, 2023, cross, vistion, using, loss, tacitile, pairs, learned, utilized, downstream, without, fine, tuning, rss, representations, sliding, deformable, surfaces, antonio, loquercio, ashish, kumar, neerja, thakkar, jitendra, malik, liability, biological, systems, evolved, limbs, legs, facilitates, postural, this, work, shows, can, high, speeds, under, external, perturbations, where, serves, manipulation, tail, promoting, stability, jaimyn, drake, joseph, ortiz, mustafa, mukadam, mike, lambeta, introduce, tvl, which, combines, paired, visual, both, annotated, vlm, generated, semantic, labels, leverage, approach, clip, aligned, encoder, finetune, open, source, llm, description, our, results, show, incorporating, information, allows, significantly, outperform, state, art, vlms, including, label, generating, model, understanding, icml, multimodal, fangchen, liu, hui, explore, enhance, models, perform, icrt, causal, generalizes, unseen, conditioned, prompts, sensorimotor, trajectories, new, composing, image, states, tuples, collected, through, teleoperation, preprint, 2408, 15980, via, selected, publications, google, scholar, email, postdoc, stanford, jiajun, obtained, phd, degree, eecs, berkeley, research, focuses, general, recently, have, worked, robotics, between, whole, body, quadruped,
Text of the page (random words):
huang raven huang huang raven huang i am a postdoc at stanford advised by prof jiajun wu and prof fei fei li i obtained my phd degree in eecs at uc berkeley advised by prof ken goldberg my research focuses on general robot learning recently i have worked on the in context learning of robotics the alignment between tactile vision and language and the whole body control of a quadruped email nbsp nbsp google scholar selected publications your browser does not support the video tag in context imitation learning via next token prediction letian fu huang huang gaurav datta lawrence yunliang chen william chung ho panitch fangchen liu hui li ken goldberg equal contribution arxiv preprint arxiv 2408 15980 2024 website we explore how to enhance next token prediction models to perform in context imitation learning on a real robot we propose in context robot transformer icrt a causal transformer that generalizes to unseen tasks conditioned on prompts of sensorimotor trajectories of the new task composing of image observations actions and states tuples collected through human teleoperation a touch vision and language dataset for multimodal alignment letian fu gaurav datta huang huang william chung ho panitch jaimyn drake joseph ortiz mustafa mukadam mike lambeta roberto calandra ken goldberg equal contribution icml 2024 oral presentation website we introduce the touch vision language tvl dataset which combines paired tactile and visual observations with both human annotated and vlm generated tactile semantic labels we then leverage a contrastive learning approach to train a clip aligned tactile encoder and finetune an open source llm for a tactile description task our results show that incorporating tactile information allows us to significantly outperform state of the art vlms including the label generating model on a tactile understanding task your browser does not support the video tag manipulator as a tail promoting dynamic stability for legged locomotion huang huang antonio loquercio ashish kumar neerja thakkar ken goldberg jitendra malik icra 2024 website for locomotion is an arm on a legged robot a liability or an asset for locomotion biological systems evolved additional limbs beyond legs that facilitates postural control this work shows how a manipulator can be an asset for legged locomotion at high speeds or under external perturbations where the arm serves beyond manipulation learning self supervised representations from vision and touch for active sliding perception of deformable surfaces justin kerr huang huang albert wilcox ryan hoque jeffrey ichnowski roberto calandra and ken goldberg equal contribution rss 2023 paper we learn a self supervised representation cross tactile and vistion using contrastive loss we collect vision tacitile pairs in a self supervised way in real the learned representation is utilized in the downstream active perception tasks without fine tuning your browser does not support the video tag evo nerf evolving nerf for sequential robot grasping justin kerr letian fu huang huang yahav avigal matthew tancik jeffrey ichnowski angjoo kanazawa ken goldberg corl 2022 oral presentation openreview we propose evo nerf with additional geometry regularizations improving performance in rapid capture settings to achieve real time updateable scene reconstruction for rapidly grasping table top transparent objects we train a nerf adapted grasping network learns to ignore floaters your browser does not support the video tag real2sim2real self supervised learning of physical single step dynamic actions for planar robot casting vincent lim huang huang lawrence yunliang chen jonathan wang jeffrey ichnowski daniel seita michael laskey ken goldberg equal contribution icra 2021 paper we collect planar robot casting data in real in a self supervised way to tune the simulation in isaac gym we then collect more data in the tuned simulator combined with upsampled real data we learn a policy for planar robot casting to reach to a given target attaining median error distance as of cable length ranging from 8 to 14
|
