_version_ 1866909248517046272
author Yenamandra, Sriram
Ramachandran, Arun
Khanna, Mukul
Yadav, Karmesh
Vakil, Jay
Melnik, Andrew
Büttner, Michael
Harz, Leon
Brown, Lyon
Nandi, Gora Chand
PS, Arjun
Yadav, Gaurav Kumar
Kala, Rahul
Haschke, Robert
Luo, Yang
Zhu, Jinxin
Han, Yansen
Lu, Bingyi
Gu, Xuan
Liu, Qinyuan
Zhao, Yaping
Ye, Qiting
Dou, Chenxiao
Chua, Yansong
Kuzma, Volodymyr
Humennyy, Vladyslav
Partsey, Ruslan
Francis, Jonathan
Chaplot, Devendra Singh
Chhablani, Gunjan
Clegg, Alexander
Gervet, Theophile
Jain, Vidhi
Ramrakhya, Ram
Szot, Andrew
Wang, Austin
Yang, Tsung-Yen
Edsinger, Aaron
Kemp, Charlie
Shah, Binit
Kira, Zsolt
Batra, Dhruv
Mottaghi, Roozbeh
Bisk, Yonatan
Paxton, Chris
author_facet Yenamandra, Sriram
Ramachandran, Arun
Khanna, Mukul
Yadav, Karmesh
Vakil, Jay
Melnik, Andrew
Büttner, Michael
Harz, Leon
Brown, Lyon
Nandi, Gora Chand
PS, Arjun
Yadav, Gaurav Kumar
Kala, Rahul
Haschke, Robert
Luo, Yang
Zhu, Jinxin
Han, Yansen
Lu, Bingyi
Gu, Xuan
Liu, Qinyuan
Zhao, Yaping
Ye, Qiting
Dou, Chenxiao
Chua, Yansong
Kuzma, Volodymyr
Humennyy, Vladyslav
Partsey, Ruslan
Francis, Jonathan
Chaplot, Devendra Singh
Chhablani, Gunjan
Clegg, Alexander
Gervet, Theophile
Jain, Vidhi
Ramrakhya, Ram
Szot, Andrew
Wang, Austin
Yang, Tsung-Yen
Edsinger, Aaron
Kemp, Charlie
Shah, Binit
Kira, Zsolt
Batra, Dhruv
Mottaghi, Roozbeh
Bisk, Yonatan
Paxton, Chris
contents In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed Open Vocabulary Mobile Manipulation as a key benchmark task for robotics: finding any object in a novel environment and placing it on any receptacle surface within that environment. We organized a NeurIPS 2023 competition featuring both simulation and real-world components to evaluate solutions to this task. Our baselines on the most challenging version of this task, using real perception in simulation, achieved only an 0.8% success rate; by the end of the competition, the best participants achieved an 10.8\% success rate, a 13x improvement. We observed that the most successful teams employed a variety of methods, yet two common threads emerged among the best solutions: enhancing error detection and recovery, and improving the integration of perception with decision-making processes. In this paper, we detail the results and methodologies used, both in simulation and real-world settings. We discuss the lessons learned and their implications for future research. Additionally, we compare performance in real and simulated environments, emphasizing the necessity for robust generalization to novel settings.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06939
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge
Yenamandra, Sriram
Ramachandran, Arun
Khanna, Mukul
Yadav, Karmesh
Vakil, Jay
Melnik, Andrew
Büttner, Michael
Harz, Leon
Brown, Lyon
Nandi, Gora Chand
PS, Arjun
Yadav, Gaurav Kumar
Kala, Rahul
Haschke, Robert
Luo, Yang
Zhu, Jinxin
Han, Yansen
Lu, Bingyi
Gu, Xuan
Liu, Qinyuan
Zhao, Yaping
Ye, Qiting
Dou, Chenxiao
Chua, Yansong
Kuzma, Volodymyr
Humennyy, Vladyslav
Partsey, Ruslan
Francis, Jonathan
Chaplot, Devendra Singh
Chhablani, Gunjan
Clegg, Alexander
Gervet, Theophile
Jain, Vidhi
Ramrakhya, Ram
Szot, Andrew
Wang, Austin
Yang, Tsung-Yen
Edsinger, Aaron
Kemp, Charlie
Shah, Binit
Kira, Zsolt
Batra, Dhruv
Mottaghi, Roozbeh
Bisk, Yonatan
Paxton, Chris
Robotics
Computer Vision and Pattern Recognition
In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed Open Vocabulary Mobile Manipulation as a key benchmark task for robotics: finding any object in a novel environment and placing it on any receptacle surface within that environment. We organized a NeurIPS 2023 competition featuring both simulation and real-world components to evaluate solutions to this task. Our baselines on the most challenging version of this task, using real perception in simulation, achieved only an 0.8% success rate; by the end of the competition, the best participants achieved an 10.8\% success rate, a 13x improvement. We observed that the most successful teams employed a variety of methods, yet two common threads emerged among the best solutions: enhancing error detection and recovery, and improving the integration of perception with decision-making processes. In this paper, we detail the results and methodologies used, both in simulation and real-world settings. We discuss the lessons learned and their implications for future research. Additionally, we compare performance in real and simulated environments, emphasizing the necessity for robust generalization to novel settings.
title Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.06939