DC Field | Value | Language |
---|---|---|
dc.contributor.author | Gao, Mengyi | ko |
dc.contributor.author | Chang, Dong Eui | ko |
dc.date.accessioned | 2021-11-30T06:49:50Z | - |
dc.date.available | 2021-11-30T06:49:50Z | - |
dc.date.created | 2021-11-30 | - |
dc.date.created | 2021-11-30 | - |
dc.date.created | 2021-11-30 | - |
dc.date.created | 2021-11-30 | - |
dc.date.issued | 2021-10-13 | - |
dc.identifier.citation | 21st International Conference on Control, Automation and Systems (ICCAS), pp.1360 - 1364 | - |
dc.identifier.issn | 2093-7121 | - |
dc.identifier.uri | http://hdl.handle.net/10203/289702 | - |
dc.description.abstract | In this paper, we implement a modified SAC [1] algorithm for autonomous driving tasks using the simulator AirSim's [2] environment API which provides various weather, collision, and lighting choices. Given current image state and car velocity as our inputs, the task outputs the throttle, brake, and steering angle data and gives the vehicle action instruction through the AirSim control outputs. As autonomous vehicles are more likely to be accepted if they drive like how human would, we at first train our model by imitation learning to provides the pre-trained human-like policy and weights to SAC. During the reinforcement learning, in order to increase the feasible policy's robustness, we use ResNet-34 [3] as our actor and critic network architecture in the SAC algorithm. | - |
dc.language | English | - |
dc.publisher | ICROS (Institute of Control, Robotics and Systems) | - |
dc.title | Autonomous Driving based on Modified SAC Algorithm through Imitation Learning Pretraining | - |
dc.type | Conference | - |
dc.identifier.wosid | 000750950700174 | - |
dc.identifier.scopusid | 2-s2.0-85124246804 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1360 | - |
dc.citation.endingpage | 1364 | - |
dc.citation.publicationname | 21st International Conference on Control, Automation and Systems (ICCAS) | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | Ramada Plaza Hotel & Online | - |
dc.identifier.doi | 10.23919/ICCAS52745.2021.9649939 | - |
dc.contributor.localauthor | Chang, Dong Eui | - |
dc.contributor.nonIdAuthor | Gao, Mengyi | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.