Deep Multi-Agent Reinforcement Learning for Decision Making in Autonomous Driving Systems

A high intelligence decision-making system is crucial for urban autonomous driving with dense surrounding dynamic objects. It must be able to handle the complex road geometry and topology, complex multi-agent interactions, and accurately follow the high-level commands such as routing information. The vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, passing an intersection, taking left and right turns and while pushing ahead in unstructured urban roadways. Also, the vehicle must balance between the unpredictable behavior of other agents in this multi-agent scenario and at the same time not to be too defensive so that normal traffic flow is maintained.

The purpose of this project is to present and develop efficient machine learning-based approaches to solve the decision-making problem in autonomous driving systems in multi-agent environments.

People involved

  • Daulet Baimukashev (daulet.baimukashev@aalto.fi), doctoral candidate.
  • Gokhan Alcan (gokhan.alcan@aalto.fi), postdoctoral researcher.
  • Eshagh Kargar (eshagh.kargar@aalto.fi), doctoral candidate.
  • Ville Kyrki (ville.kyrki@aalto.fi), professor.

Project updates

Master Thesis on “Inverse Reinforcement Learning for Driving Behavior Modeling”

The goal of this thesis is to formulate driving behavior modeling as an inverse reinforcement learning (IRL) problem. In this context, the thesis is expected to include implementations of different IRL methods and compare them concerning prediction capabilities.

Master Thesis on “Interaction Modeling for Autonomous Driving Using Graph Neural Networks”

The goal of this thesis is to model the interactions among autonomous agents in dense traffic using GNN. In this context, the thesis is expected to include an ablation study to identify which input features (such as velocity, distance to other vehicles, etc.) has the maximum effect on prediction and the effects of changing the graph structure on the interactions among the vehicles.

Deep Multi-Agent Reinforcement Learning for Decision Making in Autonomous Driving Systems

A high intelligence decision-making system is crucial for urban autonomous driving with dense surrounding dynamic objects. It must be able to handle the complex road geometry and topology, complex multi-agent interactions, and accurately follow the high-level commands such as routing information. The vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving […]