The Robotics: Science and Systems conference (RSS 2022) is taking place June 27th - July 1st, and the International Conference on Robotics and Automation (ICRA 2022) also took place just recently. We’re excited to share all the work from SAIL that’s being presented, and you’ll find links to papers, videos and blogs below. Feel free to reach out to the contact authors directly to learn more about the work that’s happening at Stanford!

List of Accepted Papers (ICRA)

ReachBot: A Small Robot with Exceptional Reach for Rough Terrain

Authors: Tony G. Chen, Becky Miller, Crystal Winston, Stephanie Newdick, Andrew Bylard, Marco Pavone, Mark R. Cutkosky
Contact: snewdick@stanford.edu
Keywords: mobile manipulation, space robotics and automation, climbing robots, grippers and other end-effectors, mechanism design

Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer

Authors: Suneel Belkhale, Ethan K. Gordon, Yuxiao Chen, Siddhartha Srinivasa, Tapomayukh Bhattacharjee, Dorsa Sadigh
Contact: belkhale@stanford.edu
Links: Paper | Website
Keywords: motion planning, human robot interaction, assistive feeding

Grounding Predicates through Actions

Authors: Toki Migimatsu, Jeannette Bohg
Contact: takatoki@cs.stanford.edu
Links: Paper | Website
Keywords: perception for manipulation, visual relationship detection, task planning

Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting

Authors: Rui Zhou, Hongyu Zhou, Huidong Gao, Masayoshi Tomizuka, Jiachen Li, Zhuo Xu
Contact: jiachen_li@stanford.edu
Links: Paper
Keywords: trajectory prediction, graph neural network, interaction modeling, human behaviors

Important Object Identification with Semi-Supervised Learning for Autonomous Driving

Authors: Jiachen Li, Haiming Gang, Hengbo Ma, Masayoshi Tomizuka, Chiho Choi
Contact: jiachen_li@stanford.edu
Links: Paper
Keywords: autonomous driving, scene understanding, relational reasoning, graph neural network

Learning Periodic Tasks from Human Demonstrations

Authors: Jingyun Yang, Junwu Zhang, Connor Settle, Akshara Rai, Rika Antonova, Jeannette Bohg
Contact: jingyuny@stanford.edu
Links: Paper | Website
Keywords: visual learning, learning from demonstration, perception for grasping and manipulation

Learning from Imperfect Demonstrations via Adversarial Confidence Transfer

Authors: Zhangjie Cao*, Zihan Wang*, Dorsa Sadigh
Contact: caozj@cs.stanford.edu
Links: Paper | Video | Website
Keywords: robotics, machine learning

Propagating State Uncertainty Through Trajectory Forecasting

Authors: Boris Ivanovic, Yifeng (Richard) Lin, Shubham Shrivastava, Punarjay Chakravarty, Marco Pavone
Contact: borisi@stanford.edu
Links: Paper
Keywords: uncertainty propagation, trajectory forecasting, autonomous vehicle perception

Symbolic State Estimation with Predicates for Contact-Rich Manipulation Tasks

Authors: Toki Migimatsu, Wenzhao Lian, Jeannette Bohg, Stefan Schaal
Contact: takatoki@cs.stanford.edu
Links: Paper | Website
Keywords: perception for manipulation, symbolic state estimation

Vision-Only Robot Navigation in a Neural Radiance World

Authors: Michal Adamkiewicz, Timothy Chen, Adam Caccavale, Rachel Gardner, Preston Culbertson, Jeannette Bohg, Mac Schwager
Contact: chengine@stanford.edu
Links: Paper | Video | Website
Keywords: neural radiance fields, nerfs, vision-only navigation

Weakly Supervised Correspondence Learning

Authors: Zihan Wang*, Zhangjie Cao*, Yilun Hao, Dorsa Sadigh
Contact: wangzih@stanford.edu
Links: Paper | Video | Website
Keywords: robotics, machine learning

List of Accepted Papers (RSS)

ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation

Authors: Bokui Shen, Zhenyu Jiang, Christopher Choy, Leonidas J. Guibas, Silvio Savarese, Anima Anandkumar, Yuke Zhu
Contact: willshen@stanford.edu
Award nominations: Best Student Paper Nomination
Links: Paper | Video | Website
Keywords: deformable manipulation, implicit representations, simulation

Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning

Authors: Maximilian Du*, Olivia Y. Lee*, Suraj Nair, Chelsea Finn
Contact: surajn@stanford.edu
Links: Paper | Video | Website
Keywords: multi-modal learning, robotic manipulation

We look forward to seeing you at the robotics conferences!