Skip to content
Snippets Groups Projects

Publications - Autonomous driving and Reinforcement Learning

Autonomous Driving

Perception pipline with classic path planning

AMZ Driverless: The Full Autonomous Racing System Visual cone detection: Mono and stereo camera. LIDAR cone detection. Cone detection with YOLO and Keypoint regression for 3d pose estimate.

Reinforcement Learning

Reinforcement Learning Approach for Formula Student Technion Driverless

CNN with VAE as state encoder. Best model SAC with continues actions space. Stacked 4 consecutive frames. Learned a model only for steering.

Deep Reinforcement Learning for Autonomous Driving DDPG Algorithm. TORCS Simulator. Simple features from the simulator. Reward: V_x*(angle)-V_y*sin(angle)-\gamma*abs(trackpose) - \beta V_x abs(trackpose)

High-speed Autonomous Drifting with Deep Reinforcement Learning State-Space model. SAC drift controller. CARLA Simulator. Features: state variables and errors between reference and current state.

End-to-End Race Driving with Deep Reinforcement Learning Features: RAW RGB image. Simulator: World rally championship game. A3C Algorithm, CNN+LSTM encoder. Reward: R = v(cos(alpha)-d) where alpha angle to track and d distance to track center.

Imitation Learning

Generative Adversarial Imitation Learning

Supervised policy learning

Reinforcement Learning

Proximal Policy Optimization Algorithms

Soft Actor-Critic

Decision Transformer
Reinforcement Learning via Sequence Modeling

Misc.

YOLOv3

YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles

Real-time 3D Pose Estimation with a Monocular Camera Using Deep Learning and Object Priors

Accurate, Low-Latency Visual Perception for Autonomous Racing: Challenges, Mechanisms, and Practical Solutions