Title:
MOVING BODY BEHAVIOR PREDICTION DEVICE AND MOVING BODY BEHAVIOR PREDICTION METHOD
Document Type and Number:
WIPO Patent Application WO/2019/124001
Kind Code:
A1
Abstract:
The present invention improves the accuracy of predicting rarely occurring behavior of moving bodies, without reducing the accuracy of predicting commonly occurring behavior of moving bodies. A vehicle 101 is provided with a moving body behavior prediction device 10. The moving body behavior prediction device 10 is provided with a first behavior prediction unit 203 and a second behavior prediction unit 207. The first behavior prediction unit 203 learns first predicted behavior 204 so as to minimize the error between behavior prediction results for moving bodies and behavior recognition results for the moving bodies after a prediction time has elapsed. The second behavior prediction unit 207 learns future second predicted behavior 208 of the moving bodies around the vehicle 101 so that the vehicle 101 does not drive in an unsafe manner.
Inventors:
ISHIKAWA MASAYOSHI (JP)
ITO HIROAKI (JP)
ITO HIROAKI (JP)
Application Number:
PCT/JP2018/043689
Publication Date:
June 27, 2019
Filing Date:
November 28, 2018
Export Citation:
Assignee:
HITACHI AUTOMOTIVE SYSTEMS LTD (JP)
International Classes:
G08G1/16; B60R21/00; G01C21/34; G06V10/764
Domestic Patent References:
| WO2004068399A1 | 2004-08-12 |
Foreign References:
| JP2011014037A | 2011-01-20 | |||
| JP2010173616A | 2010-08-12 | |||
| JP2017211913A | 2017-11-30 |
Other References:
YASUHARU KOIKE ET AL.: "A Driver Model Based on Reinforcement Learning with Multiple-Step State Estimation", (ELECTRONICS & COMMUNICATIONS IN JAPAN, PART III - FUNDAMENTALELECTRONIC SCIENCE) TRANSACTIONS OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS D-II, vol. 86, no. 10, Part 3, 2003, pages 85 - 95, XP001145276
ATSUSHI ORITA ET AL.: "A Driver Model based on Reinforcement Learning Switching Multiple Controllers", IEICE TECHNICAL REPORT, vol. 102, no. 508, 30 November 2002 (2002-11-30) - 13 December 2002 (2002-12-13), pages 71 - 76, XP009510649
WANG PIN ET AL.: "Formulation of deep reinforcement learning architecture toward autonomous driving for on-ramp merge", IEEE CONFERENCE PROCEEDINGS, vol. 2017, no. ITSC, 2017, pages 1 - 6, XP033330397, doi:10.1109/ITSC.2017.8317735
ATSUSHI ORITA ET AL.: "A Driver Model based on Reinforcement Learning Switching Multiple Controllers", IEICE TECHNICAL REPORT, vol. 102, no. 508, 30 November 2002 (2002-11-30) - 13 December 2002 (2002-12-13), pages 71 - 76, XP009510649
WANG PIN ET AL.: "Formulation of deep reinforcement learning architecture toward autonomous driving for on-ramp merge", IEEE CONFERENCE PROCEEDINGS, vol. 2017, no. ITSC, 2017, pages 1 - 6, XP033330397, doi:10.1109/ITSC.2017.8317735
Attorney, Agent or Firm:
TODA Yuji (JP)
Download PDF: