Interaction, Cooperation and Competition of Autonomous Vehicles
1Tongji University, Shanghai, China , China
2Nanyang Technological University, Singapore, Singapore , Singapore
3Tongji University, Shanghai, China
4Hong Kong Polytechnic University, Hong Kong , Hong Kong
Interaction, Cooperation and Competition of Autonomous Vehicles
Description
Due to the autonomous driving technology, the driving performance of vehicles can be improved remarkably, including safety, comfort, efficiency, and eco-driving. Therefore, autonomous vehicles (AVs) become a hot spot. Moreover, with the development of the connected driving technology, AVs can share their motion states and even intention, realizing the cooperative driving.
Despite this, there are still many challenges for decision-making and motion planning of AVs, especially in some complex mixed driving conditions. For instance, in the mixed driving environment, AV must deal with the interaction, cooperation, and competition issues with human-driven vehicles (HVs) and AVs. On the one hand, AV can cooperate with AVs, on the other hand, AV must address the competition from HVs. Different human drivers have different driving styles, yielding different interaction results for AV, which has a significant effect on the decision making of AV. To this end, the interaction-behavior characteristic modelling becomes essential before the decision-making algorithm design. To sum up, the interaction, cooperation, and competition issue is very critical in the decision-making and motion planning of AVs.
This Special Issue aims to provide recent research work, findings, perspectives, and developments related to the interaction, cooperation, and competition in the decision-making and motion planning of AVs in complex mixed driving environments.
Potential topics include but are not limited to the following:
- Trajectory prediction considering driving motivation
- Interaction-behavior characteristics modeling
- Driving intention and behavior estimation
- Behavioral decision-making in complex driving conditions
- Cooperative driving strategy for multivehicles
- Reinforcement learning driving policy
- Data-driven optimal control for AVs
- Robust motion planning in uncertain environments state estimation for autonomous driving
- Cooperative decision making and motion planning