Authors:
(1) Ruohan Zhang, Department of Computer Science, Stanford University, Institute for Human-Centered AI (HAI), Stanford University & Equally contributed; [email protected];
(2) Sharon Lee, Department of Computer Science, Stanford University & Equally contributed; [email protected];
(3) Minjune Hwang, Department of Computer Science, Stanford University & Equally contributed; [email protected];
(4) Ayano Hiranaka, Department of Mechanical Engineering, Stanford University & Equally contributed; [email protected];
(5) Chen Wang, Department of Computer Science, Stanford University;
(6) Wensi Ai, Department of Computer Science, Stanford University;
(7) Jin Jie Ryan Tan, Department of Computer Science, Stanford University;
(8) Shreya Gupta, Department of Computer Science, Stanford University;
(9) Yilun Hao, Department of Computer Science, Stanford University;
(10) Ruohan Gao, Department of Computer Science, Stanford University;
(11) Anthony Norcia, Department of Psychology, Stanford University
(12) Li Fei-Fei, 1Department of Computer Science, Stanford University & Institute for Human-Centered AI (HAI), Stanford University;
(13) Jiajun Wu, Department of Computer Science, Stanford University & Institute for Human-Centered AI (HAI), Stanford University.
Table of Links
Brain-Robot Interface (BRI): Background
Conclusion, Limitations, and Ethical Concerns
Appendix 1: Questions and Answers about NOIR
Appendix 2: Comparison between Different Brain Recording Devices
Appendix 5: Experimental Procedure
Appendix 6: Decoding Algorithms Details
Appendix 7: Robot Learning Algorithm Details
Appendix 4: Task Definitions
For systematic evaluation of task success, we provide formal definitions of our tasks in the format of BEHAVIOR Domain Definition Language (BDDL) language [69, 71]. BDDL is a predicate logic-based language that establishes a symbolic state representation built on predefined, meaningful predicates grounded in physical states [71]. Each task is defined in BDDL as an initial and goal condition parametrizing sets of possible initial states and satisfactory goal states, as shown in the figures at the end of the appendix. Compared to scene- or pose-specific definitions which are too restricted, BDDL is more intuitive to humans while providing concrete evaluation metrics for measuring task success.
This paper is available on arxiv under CC 4.0 license.