• Designed and implemented a time-sequenced Bird’s-Eye-View (BEV) model for multi-task perception, enhancing object detection, drivable space segmentation, velocity estimation, and trajectory prediction, achieving a >10% AP improvement in near-range detection.

• Developed a transformer-based post-fusion model to refine multi-sensor (LiDAR, camera, radar) detection results, enabling obstacle-level refinement and outputting motion states.

• Applied generative models (VAE, conditional diffusion models) for high-precision lane detection and VQ-VAE for efficient HD map data compression.

• Optimized backbone architectures including ResNet and Transformers, implemented custom variants with tailored hyperparameters to maximize performance.

• Deployed models on embedded systems via ONNX/TensorRT conversion, accelerating inference through quantization and enhancing accuracy via Quantization-Aware Training (QAT).

• Pioneered initiatives for A-star searching path planning and least-square curve fitting for trajectory planning

• Excelled in maximizing tracking performance by integrating and comparing PID, MPC, LQR controller

• Used YOLO convolutional network and PyTorch based model for pedestrian, vehicle detection, and depth estimation

Topic: Image Reconstruction Using Machine Learning

• Constructed the lens-less camera with only a CMOS image sensor.

• Collected the training images and labels from capturing a LED matrix board.

• Developed the deep learning method based on Keras and trained the images.

• Reconstructed the original images from the blurred images taken by the image sensor.

• Designed and improved the control algorithm of the quadruped robot.

• Trained the quadruped robot with reinforcement learning.

• Adjust the physical design and parameters of the quadruped robot.

Supervised by Professor Yon Visell at RE Touch Lab

Topic: Multi-dimensional Skin Stretch Feedback for Prosthetic Hands by Haptic Rocker

• Designed the mechanical structure of one-dimensional and multi-dimensional haptic device.

• Made the haptic devices by 3D-printing and servo motors.

• Constructed the feedback algorithms and created feelings at the upper arm corresponding to the signals received by the prosthetic hands.

• Tested and evaluated the proprioceptive information generated by the feedback device.