Register now After registration you will be able to apply for this opportunity online.
Reinforcement Learning for Go-Kart Racing
Our aim is to create an autonomous racing system capable of swiftly learning optimal racing strategies and navigating tracks more effectively (faster) than traditional methods and human drivers using RL.
Reinforcement learning (RL) models devoid of explicit models have showcased remarkable superiority over classical planning and control strategies. This advantage is attributed to their advanced exploration capabilities, enabling them to efficiently discover new optimal trajectories. Leveraging RL, our aim is to create an autonomous racing system capable of swiftly learning optimal racing strategies and navigating tracks more effectively (faster) than traditional methods and human drivers.
Reinforcement learning (RL) models devoid of explicit models have showcased remarkable superiority over classical planning and control strategies. This advantage is attributed to their advanced exploration capabilities, enabling them to efficiently discover new optimal trajectories. Leveraging RL, our aim is to create an autonomous racing system capable of swiftly learning optimal racing strategies and navigating tracks more effectively (faster) than traditional methods and human drivers.
Objective:
The primary objective of this project is to design and implement an RL-based system capable of autonomously racing a real go-kart around a track. Specifically, we aim to achieve the following goals:
1. Create a realistic simulation environment that accurately captures the dynamics of the autonomous go-kart platform, including its sensor readings, and its interactions with the racing track.
2. Implement and train the RL algorithms to learn optimal racing trajectories, braking points, to maximize its lap time performance. (No overtaking policies will be explored in this phase)
3. Deploy the RL algorithm on the real platform.
4. Design an experimental campaign to evaluate the autonomous agent's performance compared to classical planning and control strategies, and human drivers.
Required Background and Knowledges
ROS, Python, C++ is a plus
RL (simulation, deployment)
Sensor modeling and system identification
Hands on experience with real robots and RL
Objective: The primary objective of this project is to design and implement an RL-based system capable of autonomously racing a real go-kart around a track. Specifically, we aim to achieve the following goals: 1. Create a realistic simulation environment that accurately captures the dynamics of the autonomous go-kart platform, including its sensor readings, and its interactions with the racing track. 2. Implement and train the RL algorithms to learn optimal racing trajectories, braking points, to maximize its lap time performance. (No overtaking policies will be explored in this phase) 3. Deploy the RL algorithm on the real platform. 4. Design an experimental campaign to evaluate the autonomous agent's performance compared to classical planning and control strategies, and human drivers.
Required Background and Knowledges ROS, Python, C++ is a plus RL (simulation, deployment) Sensor modeling and system identification Hands on experience with real robots and RL
The project will be supervised by both Professor Emilio Frazzoli and Professor Davide Scaramuzza's groups. The experiments will take place at the Winterthur testing ground, utilizing our fleet of autonomous racing karts. Interested candidates should send their CV, transcripts (bachelor and master), and descriptions of relevant projects to Angel Romero (roagui AT ifi DOT uzh DOT ch), Leonard Bauersfeld (bauersfeld AT ifi DOT uzh DOT ch), Ismail Geles (geles AT ifi DOT uzh DOT ch), Jiaxu Xing (xing AT ifi DOT uzh DOT ch) and Maurilio di Cicco (mdicicco AT ethz DOT ch)
The project will be supervised by both Professor Emilio Frazzoli and Professor Davide Scaramuzza's groups. The experiments will take place at the Winterthur testing ground, utilizing our fleet of autonomous racing karts. Interested candidates should send their CV, transcripts (bachelor and master), and descriptions of relevant projects to Angel Romero (roagui AT ifi DOT uzh DOT ch), Leonard Bauersfeld (bauersfeld AT ifi DOT uzh DOT ch), Ismail Geles (geles AT ifi DOT uzh DOT ch), Jiaxu Xing (xing AT ifi DOT uzh DOT ch) and Maurilio di Cicco (mdicicco AT ethz DOT ch)