Yikai Wang 王毅楷

I am a senior undergraduate student at the Weiyang College, Tsinghua University, where my major is Mechanical Engineering, as well as Mathematics and Physics.

I am a reserch assistant at the ISR Lab, IIIS, Tsinghua University and a student intern at Carnegie Mellon University. I am honored to be advised by Prof.Jianyu Chen, Prof. Guanya Shi, and Prof.Ding Zhao.

I aim to empower robots to explore the unstructured environments in the real world agilely and safely through synthesizing principles from deep learning and control theory. Currently, my interests revolve around two questions: a) Can data pave the way to success? and b) How can models and optimization be utilized in this context?

I am seeking PhD positions beginning Fall 2024!

Email  /  CV(12/01/2023)  /  Google Scholar

Research

Guardians as You Fall: Active Mode Transition for Safe Falling

We propose Guardians as You Fall (GYF), a safe falling/tumbling and recovery framework that can actively tumble and recover to stable modes to reduce damage in highly dynamic scenarios. The key idea of GYF is to adaptively traverse across different stable modes via active tumbling, before the robot shifts to irrecoverable poses. GYF offers a new perspective on safe falling and recovery in locomotion tasks, which potentially enables much more aggressive explorations of existing agile locomotion skills.

Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild

We propose a new framework for learning robust, agile and natural legged locomotion skills over challenging terrain with only proprioceptive perception. We incorporate an adversarial training branch based on real animal locomotion data upon a teacher-student training pipeline for robust sim-to-real transfer. To the best of our understanding, this is the first learning-based method enabling quadrupedal robots to gallop in the wild.

The Minimum Number of DoFs Required for the Robot to Keep Balance?

We aim to use the minimum DoFs to keep the robot standing and utilize the remaining DoFs to accomplish the manipulation tasks. Our current approach involves utilizing RL to generate offset outputs and employing QP for precise low-level control. Consequently, the robot can maintain balance using solely the 6 DoFs of its hind legs.

Projects

Building an autonomous picking car from scratch

Design and built a car that is capable of autonomous navigation, picking and storing certain yellow objects and unloading them in the designated area. Target recognition was accomplished by a monocular camera and image algorithms. Picking and unloading were accomplished with 3 parallel elastic ropes and a steering engine. Velocities were adjusted using PID control. Mechanical parts were designed using Solidworks, and manufactured by 3D-printing/laser cutting.

Design and source code from Jon Barron's website