TY - GEN
T1 - Learning Task-Based Instructional Policy for Excavator-Like Robots
AU - Maske, Harshal
AU - Kieson, Emily
AU - Chowdhary, Girish
AU - Abramson, Charles
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/10
Y1 - 2018/9/10
N2 - We explore beyond existing work in learning from demonstration by asking the question: 'Can robots learn to guide?', that is, can a robot autonomously learn an instructional policy from expert demonstration and use it to instruct humans in executing complex task? As a solution, we propose learning of instructional policy (pi^ I ) that maps the state to an instruction for a human. To learn pi^ I , we define action primitives that addresses the challenge of mapping continuous state action trajectories to human parse-able instructions. Action primitives are demonstrated to be very effective in automatic segmentation of demonstration trajectories into fewer repetitive and reusable segments, and a highly scalable approach in comparison to the existing state-of-the art. Finally, we construct a non-generic policy model as a generative model for instructional policies to generate instruction for an entire task. With few modifications, the proposed model is demonstrated to perform autonomous execution of complex truck loading task on hydraulic actuated scaled excavator robot. Guidance approach is tested based on a controlled group study involving 75 participants, who learn to perform the same task.
AB - We explore beyond existing work in learning from demonstration by asking the question: 'Can robots learn to guide?', that is, can a robot autonomously learn an instructional policy from expert demonstration and use it to instruct humans in executing complex task? As a solution, we propose learning of instructional policy (pi^ I ) that maps the state to an instruction for a human. To learn pi^ I , we define action primitives that addresses the challenge of mapping continuous state action trajectories to human parse-able instructions. Action primitives are demonstrated to be very effective in automatic segmentation of demonstration trajectories into fewer repetitive and reusable segments, and a highly scalable approach in comparison to the existing state-of-the art. Finally, we construct a non-generic policy model as a generative model for instructional policies to generate instruction for an entire task. With few modifications, the proposed model is demonstrated to perform autonomous execution of complex truck loading task on hydraulic actuated scaled excavator robot. Guidance approach is tested based on a controlled group study involving 75 participants, who learn to perform the same task.
UR - http://www.scopus.com/inward/record.url?scp=85063124703&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063124703&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2018.8462923
DO - 10.1109/ICRA.2018.8462923
M3 - Conference contribution
AN - SCOPUS:85063124703
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 1962
EP - 1969
BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018
Y2 - 21 May 2018 through 25 May 2018
ER -