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

  • Eshagh Kargar (eshagh.kargar@aalto.fi), PhD student.
  • Andrei Aksjonov (andrei.aksjonov@aalto.fi), postdoctoral researcher.
  • Ville Kyrki (ville.kyrki@aalto.fi), professor.

Project updates

Master Thesis on “High-Level Decision Making in Self-Driving Cars using Deep Reinforcement Learning”

Decision-making is one of the most important modules in a self-driving car system and navigating an autonomous car in a dynamic and multi-agent urban scenario needs to understand the scene and the interaction between agents. One way to do the scene understanding is to use Graph Neural Networks (GNNs) to learn the interaction between agents […]

Scene Representation Learning for Decision-Making in Autonomous Driving Systems using Graph Neural Networks

Navigating a self-driving car in dense urban scenarios is a multi-agent decision-making problem and understanding the scene and agents around the car and also the interaction between them is very important for decision-making. One solution to do this scene understanding is to use Graph Neural Networks (GNNs) and create an embedded vector for the decision-making […]

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 […]