Vision-based End-to-end Control for Racing
Nov 1, 2023
·
1 min read
Principal Researcher (Nov 2023 — May 2024)
- Developed a CNN-based end-to-end controller for high-speed autonomous racing using RGB camera input and velocity feedback.
- Trained using imitation learning from MPCC expert trajectories and deployed on a 1:10 Jetson-powered vehicle with onboard ROS stack.
- Designed and executed systematic policy evaluation in CARLA under various conditions (e.g., weather, lighting), measuring success rates and failure modes across diverse initial conditions to assess robustness near dynamic handling limits.
- Achieved long rollouts (80 laps at high speed) without constraint violation and improved consistency in performance compared to traditional SLAM-based pipelines across 10+ field tests.
Tech: PyTorch, CasADi, ROS, OpenCV, SLAM, RL, NVIDIA Jetson, real-time control.
Authors
Shengfan Cao
(he/him)
PhD Researcher in Autonomous Driving & Robotics
PhD researcher with 3+ years of hands-on experience in autonomous driving and robotic systems, spanning safe learning, control, and end-to-end autonomy deployment. I am transitioning into industry to work where large-scale data and real-world constraints continuously shape and validate learning-based autonomous systems.