Workshop
7th Robot Learning Workshop: Towards Robots with Human-Level Abilities
Andrey Kolobov · Hamidreza Kasaei · Alex Bewley · Anqi Li · Dhruv Shah · Georgia Chalvatzaki · Feras Dayoub · Roberto Calandra · Ted Xiao · Rika Antonova · Nur Muhammad Shafiullah · Masha Itkina
Garnet 216-217
Sat 26 Apr, 5:55 p.m. PDT
The year 2024 has seen an explosion of interest in humanoid robots. In the 7th Robot Learning workshop, to be held at ICLR-2025, we will look beyond the humanoid embodiment and ask: how far are we from robots with human-level abilities? What do we need to improve about embodied learning, decision-making, perception, and data collection to train generally physically capable robots to robustly perform a wide range of activities such as cooking or tidying up the house -- activities that people do without much thinking? We believe many of the weaknesses of the current robotic systems to be a reflection of the shortcomings of general AI methods and models. As such, in this workshop we will seek diverse perspectives from robotics-focused and robotics-orthogonal parts of the ICLR community alike, scientific contributions from academia and industry, as well as participants from a variety of backgrounds and career stages. Capitalizing on our prior experience with robotics showcases, in keeping with the spirit of the times we will solicit several humanoid robotics companies to exhibit their robots during the workshop's poster sessions.
Schedule
Sat 5:55 p.m. - 6:00 p.m.
|
Opening remarks
(
Intro
)
>
SlidesLive Video |
🔗 |
Sat 6:00 p.m. - 6:15 p.m.
|
Best Paper Award talk
(
Contributed paper talk
)
>
SlidesLive Video |
🔗 |
Sat 6:15 p.m. - 6:40 p.m.
|
Spotlight paper talks session #1
(
Contributed paper talks
)
>
SlidesLive Video |
🔗 |
Sat 6:40 p.m. - 7:40 p.m.
|
Poster & robot demo session #1 + coffee
(
Poster session
)
>
|
🔗 |
Sat 7:40 p.m. - 8:15 p.m.
|
Invited talk by Chris Paxton (Hello Robot): Towards Home Robots: Open Vocabulary Mobile Manipulation in Unstructured Environments
(
Invited talk
)
>
SlidesLive Video |
Chris Paxton 🔗 |
Sat 8:15 p.m. - 8:50 p.m.
|
Invited talk by Davide Scaramuzza & Jiaxu Xing (University of Zurich): Learning Superhuman Agile Flight
(
Invited talk
)
>
SlidesLive Video |
Davide Scaramuzza · Jiaxu Xing 🔗 |
Sat 8:50 p.m. - 9:50 p.m.
|
Lunch
(
Lunch
)
>
|
🔗 |
Sat 9:50 p.m. - 10:25 p.m.
|
Invited talk by Chelsea Finn (Stanford/Physical Intelligence): Data-Driven Pre-Training and Post-Training for Robot Foundation Models
(
Invited talk
)
>
SlidesLive Video |
Chelsea Finn 🔗 |
Sat 10:25 p.m. - 11:00 p.m.
|
Invited talk by Sandy Huang (Google DeepMind): From agility to language understanding: Using diverse simulation to unlock real-world robot abilities
(
Invited talk
)
>
SlidesLive Video |
Sandy Huang 🔗 |
Sat 11:00 p.m. - 11:35 p.m.
|
Spotlight paper talks session #2
(
Contributed paper talks
)
>
SlidesLive Video |
🔗 |
Sat 11:35 p.m. - 12:35 a.m.
|
Poster & robot demo session #2 + coffee
(
Poster session
)
>
|
🔗 |
Sun 12:35 a.m. - 1:10 a.m.
|
Invited talk by David Hsu (National University of Singapore): Towards Compositional Generalization for Robot Learning
(
Invited talk
)
>
SlidesLive Video |
David Hsu 🔗 |
Sun 1:10 a.m. - 1:45 a.m.
|
Panel on the Future of Humanoid Robotics
(
Panel
)
>
SlidesLive Video |
Chaoyi Li · Niresh Dravin · Edward Johns · Animesh Garg · Sandy Huang 🔗 |
Sun 1:45 a.m. - 2:20 a.m.
|
Invited talk by Animesh Garg (Georgia Tech): Generalizeable Autonomy: Representations for Embodied Foundation Models
(
Invited talk
)
>
SlidesLive Video |
Animesh Garg 🔗 |
Sun 2:20 a.m. - 2:55 a.m.
|
Invited talk by Coline Devin (Google DeepMind): Gemini Robotics: Bringing AI into the Physical World
(
Invited talk
)
>
SlidesLive Video |
Coline Devin 🔗 |
Sun 2:55 a.m. - 3:00 a.m.
|
Closing remarks
(
Closing remarks
)
>
SlidesLive Video |
🔗 |
-
|
Continuous Scene Graph Generation for Imitation Learning of Everyday Tasks ( Poster ) > link | Maëlic Neau · Paulo Santos · Anne-Gwenn Bosser · Cedric Buche 🔗 |
-
|
World Models as Reference Trajectories for Rapid Motor Adaptation ( Poster ) > link | Carlos Brito · Daniel McNamee 🔗 |
-
|
RL Zero: Zero-Shot Language to Behaviors without any Supervision ( Poster ) > link | Harshit Sikchi · Siddhant Agarwal · Pranaya Jajoo · Samyak Parajuli · Caleb Chuck · Max Rudolph · Peter Stone · Amy Zhang · Scott Niekum 🔗 |
-
|
Value-Based Deep RL Scales Predictably ( Poster ) > link | Oleh Rybkin · Michal Nauman · Preston Fu · Charlie Snell · Pieter Abbeel · Sergey Levine · Aviral Kumar 🔗 |
-
|
Value-Based Deep RL Scales Predictably ( Oral ) > link | Oleh Rybkin · Michal Nauman · Preston Fu · Charlie Snell · Pieter Abbeel · Sergey Levine · Aviral Kumar 🔗 |
-
|
Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning ( Poster ) > link | Egor Cherepanov · Nikita Kachaev · Aleksey Kovalev · Aleksandr Panov 🔗 |
-
|
Student-Informed Teacher Training ( Poster ) > link | Nico Messikommer · Jiaxu Xing · Elie Aljalbout · Davide Scaramuzza 🔗 |
-
|
A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control ( Poster ) > link | Nikita Kachaev · Daniil Zelezetsky · Aleksey Kovalev · Aleksandr Panov 🔗 |
-
|
Universal Actions for Enhanced Embodied Foundation Models ( Poster ) > link | Jinliang Zheng · Jianxiong Li · Dongxiu Liu · Yinan Zheng · Zhihao Wang · Zhonghong Ou · Yu Liu · Jingjing Liu · Ya-Qin Zhang · Xianyuan Zhan 🔗 |
-
|
Stress-Testing Offline Reward-Free Reinforcement Learning: A Case for Planning with Latent Dynamics Models ( Poster ) > link | Vlad Sobal · Wancong Zhang · Kyunghyun Cho · Randall Balestriero · Tim G. J. Rudner · Yann LeCun 🔗 |
-
|
FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies ( Poster ) > link | Moritz Reuss · Hongyi Zhou · Marcel Rühle · Ömer Yağmurlu · Fabian Otto · Rudolf Lioutikov 🔗 |
-
|
ANYDEXGRASP: LEARNING GENERAL DEXTEROUS GRASPING FOR ANY HANDS WITH HUMAN-LEVEL LEARNING EFFICIENCY ( Poster ) > link | Hao-Shu Fang · Hengxu Yan · Zhenyu Tang · Hongjie Fang · Chenxi Wang · Cewu Lu 🔗 |
-
|
AUTOEVAL: AUTONOMOUS EVALUATION OF GENERALIST ROBOT MANIPULATION POLICIES IN THE REAL WORLD ( Poster ) > link | Zhiyuan Zhou · Pranav Atreya · You Liang Tan · Karl Pertsch · Sergey Levine 🔗 |
-
|
AUTOEVAL: AUTONOMOUS EVALUATION OF GENERALIST ROBOT MANIPULATION POLICIES IN THE REAL WORLD ( Oral ) > link | Zhiyuan Zhou · Pranav Atreya · You Liang Tan · Karl Pertsch · Sergey Levine 🔗 |
-
|
Achieving Human Level Competitive Robot Table Tennis ( Poster ) > link |
27 presentersDavid D'Ambrosio · Saminda Abeyruwan · Laura Graesser · Atil Iscen · Heni Ben Amor · Alex Bewley · Barney Reed · Krista Reymann · Leila Takayama · Yuval Tassa · Krzysztof Choromanski · Erwin Coumans · Deepali Jain · Navdeep Jaitly · Natasha Jaques · Satoshi Kataoka · Yuheng Kuang · Nevena Lazic · Reza Mahjourian · Sherry Moore · Kenneth Oslund · Anish Shankar · Vikas Sindhwani · Vincent Vanhoucke · Grace Vesom · Peng Xu · Pannag Sanketi |
-
|
PP-Tac: Paper Picking Using Omnidirectional Tactile Feedback in Dexterous Robotic Hands ( Poster ) > link | Pei Lin · Yuzhe Huang · Wanlin Li · Jianpeng Ma · Chenxi Xiao · Ziyuan Jiao 🔗 |
-
|
PP-Tac: Paper Picking Using Omnidirectional Tactile Feedback in Dexterous Robotic Hands ( Oral ) > link | Pei Lin · Yuzhe Huang · Wanlin Li · Jianpeng Ma · Chenxi Xiao · Ziyuan Jiao 🔗 |
-
|
Self-supervised Visual State Representation Learning for robotics from Dynamic Scenes ( Poster ) > link | Taekyung Kim · JeongEun Park · Sangdoo Yun · Dongyoon Han · Byeongho Heo 🔗 |
-
|
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning ( Poster ) > link | Moritz Reuss · Jyothish Pari · Pulkit Agrawal · Rudolf Lioutikov 🔗 |
-
|
SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation ( Poster ) > link | Haoquan Fang · Markus Grotz · Wilbert Pumacay · Yi Ru Wang · Dieter Fox · Ranjay Krishna · Jiafei Duan 🔗 |
-
|
SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation ( Oral ) > link | Haoquan Fang · Markus Grotz · Wilbert Pumacay · Yi Ru Wang · Dieter Fox · Ranjay Krishna · Jiafei Duan 🔗 |
-
|
TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning ( Poster ) > link | Ge Li · Dong Tian · Hongyi Zhou · Xinkai Jiang · Rudolf Lioutikov · Gerhard Neumann 🔗 |
-
|
RecFlow Policy: Fast and Accurate Visuomotor Policy Learning via Rectified Action Flow ( Poster ) > link | Rong Xue · Jiageng Mao · Mingtong Zhang · Yue Wang 🔗 |
-
|
RecFlow Policy: Fast and Accurate Visuomotor Policy Learning via Rectified Action Flow ( Oral ) > link | Rong Xue · Jiageng Mao · Mingtong Zhang · Yue Wang 🔗 |
-
|
Optimism via Intrinsic Rewards: Scalable and Principled Exploration for Model-based Reinforcement Learning ( Poster ) > link | Bhavya · Lenart Treven · Carmelo Sferrazza · Florian Dorfler · Pieter Abbeel · Andreas Krause 🔗 |
-
|
Policy-Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone ( Poster ) > link | Max Sobol Mark · Tian Gao · Georgia Gabriela Sampaio · Mohan Kumar Srirama · Archit Sharma · Chelsea Finn · Aviral Kumar 🔗 |
-
|
Policy-Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone ( Oral ) > link | Max Sobol Mark · Tian Gao · Georgia Gabriela Sampaio · Mohan Kumar Srirama · Archit Sharma · Chelsea Finn · Aviral Kumar 🔗 |
-
|
Environment as Policy: Generative Curriculum Learning for Autonomous Racing ( Poster ) > link | Jiaxu Xing · Hongze Wang · Nico Messikommer · Davide Scaramuzza 🔗 |
-
|
Environment as Policy: Generative Curriculum Learning for Autonomous Racing ( Oral ) > link | Jiaxu Xing · Hongze Wang · Nico Messikommer · Davide Scaramuzza 🔗 |
-
|
DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning ( Poster ) > link | Zhengrong Xue · Shuying Deng · Zhenyang Chen · Yixuan Wang · Zhecheng Yuan · Huazhe Xu 🔗 |
-
|
DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning ( Oral ) > link | Zhengrong Xue · Shuying Deng · Zhenyang Chen · Yixuan Wang · Zhecheng Yuan · Huazhe Xu 🔗 |
-
|
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics ( Poster ) > link | Chan Hee Song · Valts Blukis · Jonathan Tremblay · Stephen Tyree · Yu Su · Stan Birchfield 🔗 |
-
|
Diffusion-Based Maximum Entropy Reinforcement Learning ( Poster ) > link | Onur Celik · Zechu Li · Denis Blessing · Ge Li · Daniel Palenicek · Jan Peters · Georgia Chalvatzaki · Gerhard Neumann 🔗 |
-
|
Accelerating Goal-Conditioned RL Algorithms and Research ( Poster ) > link | Michał Bortkiewicz · Władysław Pałucki · Vivek Myers · Tadeusz Dziarmaga · Tomasz Arczewski · Łukasz Kuciński · Benjamin Eysenbach 🔗 |
-
|
KineSoft: Learning Proprioceptive Manipulation Policies with Soft Robot Hands ( Poster ) > link | Uksang Yoo · Jonathan Francis · Jean Oh · Jeffrey Ichnowski 🔗 |
-
|
Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback ( Poster ) > link | Michelle Zhao · Henny Admoni · Reid Simmons · Aaditya Ramdas · Andrea Bajcsy 🔗 |
-
|
Accelerating Transformers in Online RL ( Poster ) > link | Daniil Zelezetsky · Aleksey Kovalev · Aleksandr Panov 🔗 |
-
|
Learning Long-Context Robot Policies via Past-Token Prediction ( Poster ) > link | Marcel Torne Villasevil · Andy Tang · Yuejiang Liu · Chelsea Finn 🔗 |
-
|
PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning ( Poster ) > link | Utsav Singh · Vinay Purushothaman Namboodiri 🔗 |
-
|
PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation ( Poster ) > link | Yifan Yin · Zhengtao Han · Shivam Aarya · Shuhang Xu · Jianxin Wang · Jiawei Peng · Angtian Wang · Alan Yuille · Tianmin Shu 🔗 |
-
|
Instant Policy: In-Context Imitation Learning via Graph Diffusion ( Poster ) > link | Vitalis Vosylius · Edward Johns 🔗 |
-
|
Instant Policy: In-Context Imitation Learning via Graph Diffusion ( Oral ) > link | Vitalis Vosylius · Edward Johns 🔗 |
-
|
Object-Centric Latent Action Learning ( Poster ) > link | Albina Klepach · Alexander Nikulin · Ilya Zisman · Denis Tarasov · Alexander Derevyagin · Andrei Polubarov · Lyubaykin Nikita · Vladislav Kurenkov 🔗 |
-
|
ManiSkill3: GPU Parallelized Robot Simulation and Rendering for Generalizable Embodied AI ( Poster ) > link |
23 presentersStone Tao · Fanbo Xiang · Arth Shukla · Yuzhe Qin · Xander Hinrichsen · Xiaodi Yuan · Chen Bao · Xinsong Lin · Yulin Liu · Tse-kai Chan · Yuan Gao · Xuanlin Li · Tongzhou Mu · Nan Xiao · Arnav Gurha · Viswesh N · Yong Woo Choi · Yen-Ru Chen · Zhiao Huang · Roberto Calandra · Rui Chen · Shan Luo · Hao Su |
-
|
ManiSkill3: GPU Parallelized Robot Simulation and Rendering for Generalizable Embodied AI ( Oral ) > link |
23 presentersStone Tao · Fanbo Xiang · Arth Shukla · Yuzhe Qin · Xander Hinrichsen · Xiaodi Yuan · Chen Bao · Xinsong Lin · Yulin Liu · Tse-kai Chan · Yuan Gao · Xuanlin Li · Tongzhou Mu · Nan Xiao · Arnav Gurha · Viswesh N · Yong Woo Choi · Yen-Ru Chen · Zhiao Huang · Roberto Calandra · Rui Chen · Shan Luo · Hao Su |
-
|
Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning ( Poster ) > link | Alexi Canesse · Mathieu Petitbois · Ludovic Denoyer · sylvain lamprier · Rémy Portelas 🔗 |
-
|
From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Reset-Free Unsupervised Quality-Diversity ( Poster ) > link | Luca Grillotti · Maxence Faldor · Antoine Cully 🔗 |
-
|
RILe: Reinforced Imitation Learning ( Poster ) > link | Mert Albaba · Sammy Christen · Thomas Langerak · Christoph Gebhardt · Otmar Hilliges · Michael J Black 🔗 |
-
|
Teaching Visual Language Models to Navigate using Maps ( Poster ) > link | Tigran Galstyan · Hakob Tamazyan · Narek Nurijanyan 🔗 |
-
|
Efficient Robotic Policy Learning via Latent Space Backward Planning ( Poster ) > link | Dongxiu Liu · Haoyi Niu · Zhihao Wang · Jinliang Zheng · Yinan Zheng · Zhonghong Ou · Jianming HU · Jianxiong Li · Xianyuan Zhan 🔗 |
-
|
X-IL: Exploring the Design Space of Imitation Learning Policies ( Poster ) > link |
11 presentersXiaogang Jia · Atalay Donat · Xi Huang · Xuan Zhao · Denis Blessing · Hongyi Zhou · Hanyi Zhang · Han Wang · Qian Wang · Rudolf Lioutikov · Gerhard Neumann |
-
|
X-IL: Exploring the Design Space of Imitation Learning Policies ( Oral ) > link |
11 presentersXiaogang Jia · Atalay Donat · Xi Huang · Xuan Zhao · Denis Blessing · Hongyi Zhou · Hanyi Zhang · Han Wang · Qian Wang · Rudolf Lioutikov · Gerhard Neumann |
-
|
Learning Composable Diffusion Guidance for Motion Priors ( Poster ) > link | Omkar Patil · Eric Rosen · Nakul Gopalan 🔗 |
-
|
AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons ( Poster ) > link |
14 presentersHongjie Fang · Chenxi Wang · Yiming Wang · Jingjing Chen · Shangning Xia · Jun Lv · Zihao He · Xiyan Yi · Yunhan Guo · Xinyu Zhan · Lixin Yang · Weiming Wang · Cewu Lu · Hao-Shu Fang |
-
|
AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons ( Oral ) > link |
14 presentersHongjie Fang · Chenxi Wang · Yiming Wang · Jingjing Chen · Shangning Xia · Jun Lv · Zihao He · Xiyan Yi · Yunhan Guo · Xinyu Zhan · Lixin Yang · Weiming Wang · Cewu Lu · Hao-Shu Fang |
-
|
Learning a Thousand Tasks in a Day ( Poster ) > link | Kamil Dreczkowski · Pietro Vitiello · Vitalis Vosylius · Edward Johns 🔗 |
-
|
Learning a Thousand Tasks in a Day ( Oral ) > link | Kamil Dreczkowski · Pietro Vitiello · Vitalis Vosylius · Edward Johns 🔗 |
-
|
Towards Fusing Point Cloud and Visual Representations for Imitation Learning ( Poster ) > link | Atalay Donat · Xiaogang Jia · Xi Huang · Aleksandar Taranovic · Denis Blessing · Ge Li · Hongyi Zhou · Hanyi Zhang · Rudolf Lioutikov · Gerhard Neumann 🔗 |
-
|
Small features matter: Robust representation for world models ( Poster ) > link | Zarif Ikram · Miranda Anna Christ · Ling Pan · Dianbo Liu 🔗 |
-
|
Improving Efficiency of Sampling-based Motion Planning via Message-Passing Monte Carlo ( Poster ) > link | Makram Chahine · T. Konstantin Rusch · Zach Patterson · Daniela Rus 🔗 |
-
|
ControlManip: Few-Shot Manipulation Fine-tuning via Object-centric Conditional Control ( Poster ) > link | Puhao Li · Yingying Wu · Wanlin Li · Yuzhe Huang · Zhiyuan Zhang · Yinghan Chen · Song-Chun Zhu · Tengyu Liu · Siyuan Huang 🔗 |
-
|
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING ( Poster ) > link |
22 presentersConnor Schenck · Isaac Reid · Mithun George Jacob · Alex Bewley · Joshua Ainslie · David Rendleman · Deepali Jain · Mohit Sharma · Kumar Dubey · Ayzaan Wahid · Sumeet Singh · René Wagner · Tianli Ding · Chuyuan Fu · Arunkumar Byravan · Jake Varley · Alexey Gritsenko · Matthias Minderer · Dmitry Kalashnikov · Jonathan Tompson · Vikas Sindhwani · Krzysztof Choromanski |
-
|
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING ( Oral ) > link |
22 presentersConnor Schenck · Isaac Reid · Mithun George Jacob · Alex Bewley · Joshua Ainslie · David Rendleman · Deepali Jain · Mohit Sharma · Kumar Dubey · Ayzaan Wahid · Sumeet Singh · René Wagner · Tianli Ding · Chuyuan Fu · Arunkumar Byravan · Jake Varley · Alexey Gritsenko · Matthias Minderer · Dmitry Kalashnikov · Jonathan Tompson · Vikas Sindhwani · Krzysztof Choromanski |
-
|
Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation ( Poster ) > link | Nolan Fey · Gabriel Margolis · Martin Peticco · Pulkit Agrawal 🔗 |
-
|
Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation ( Oral ) > link | Nolan Fey · Gabriel Margolis · Martin Peticco · Pulkit Agrawal 🔗 |