Sökning: id:"swepub:oai:DiVA.org:kth-256310" >
Deep Reinforcement ...
Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments
-
- Chen, Xi (författare)
- KTH,Robotik, perception och lärande, RPL
-
- Ghadirzadeh, Ali (författare)
- KTH,Robotik, perception och lärande, RPL
-
- Folkesson, John, Associate Professor, 1960- (författare)
- KTH,Robotik, perception och lärande, RPL,RPL/EECS
-
visa fler...
-
- Björkman, Mårten, 1970- (författare)
- KTH,Robotik, perception och lärande, RPL
-
- Jensfelt, Patric, 1972- (författare)
- KTH,Robotik, perception och lärande, RPL
-
visa färre...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2018
- 2018
- Engelska.
-
Ingår i: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781538680940
- Relaterad länk:
-
http://10.1109/IROS....
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multifaceted navigation skill by learning and exploiting a number of manageable navigation behaviors. We also introduce a domain randomization technique to improve the versatility of the training samples. We demonstrate experimentally a significant improvement in terms of data-efficiency, success rate, robustness against irrelevant sensory data, and also the quality of the maneuver skills.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)
Nyckelord
- Computer Science
- Datalogi
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas