Title:
ROBOT CONTROL MODEL LEARNING METHOD, ROBOT CONTROL MODEL LEARNING DEVICE, ROBOT CONTROL MODEL LEARNING PROGRAM, ROBOT CONTROL METHOD, ROBOT CONTROL DEVICE, ROBOT CONTROL PROGRAM, AND ROBOT
Document Type and Number:
WIPO Patent Application WO/2021/095464
Kind Code:
A1
Abstract:
A robot control model learning device (10) performs, by using state information indicating the state of a robot which autonomously travels to a destination in a dynamic environment as an input, reinforcement learning to obtain a robot control model for selecting and outputting a behavior in accordance with the state of the robot from among a plurality of behaviors including an intervention behavior for intervening in the environment, while using the number of times the intervention behavior has been performed as a minus reward.
More Like This:
| JP7068969 | Autonomous driving system |
| JP2015103049 | MOVING BODY, AND RUNNING SYSTEM |
Inventors:
KUROSE MAI (JP)
YONETANI RYO (JP)
YONETANI RYO (JP)
Application Number:
PCT/JP2020/039554
Publication Date:
May 20, 2021
Filing Date:
October 21, 2020
Export Citation:
Assignee:
OMRON TATEISI ELECTRONICS CO (JP)
International Classes:
G05D1/02
Domestic Patent References:
| WO2012039280A1 | 2012-03-29 | |||
| WO2018110305A1 | 2018-06-21 |
Foreign References:
| JP2012139798A | 2012-07-26 | |||
| JP2018198012A | 2018-12-13 | |||
| JP2012187698A | 2012-10-04 | |||
| JP2019096012A | 2019-06-20 |
Other References:
DECENTRALIZED NON-COMMUNICATING MULTIAGENT COLLISION AVOIDANCE WITH DEEP REINFORCEMENT LEARNING, Retrieved from the Internet
SOCIALLY AWARE MOTION PLANNING WITH DEEP REINFORCEMENT LEARNING, Retrieved from the Internet
See also references of EP 4060446A4
SOCIALLY AWARE MOTION PLANNING WITH DEEP REINFORCEMENT LEARNING, Retrieved from the Internet
See also references of EP 4060446A4
Attorney, Agent or Firm:
TAIYO, NAKAJIMA & KATO (JP)
Download PDF: