Hi, welcome to my website! I am currently a lead robot learning engineer at Leap AI, UK. I work on robot learning,
using deep imitation learning and deep reinforcement learning to learn diverse robot skills.
Previously I also worked extensively on model-based optimization to control legged robots and robot arms, and building legged robots.
Videos of my previous work can be seen at my Youtube Channel
Please feel free to contact me if you are interested in discussing these topics with me.
Brief Bio
Previously I worked at Dyson as a senior robot research engineer. Before joining Dyson, I obtained my PhD at Imperial College London in 2022, supervised by Dr. Petar Kormushev.
My PhD focuses on bipedal locomotion and I built the bipedal robot SLIDER. I am also lucky to
work on other legged robots such as ANYmal and TALOS.
Before that, I received my Master degree in Robotics, Cognition and Intelligence from Technical University of Munich (TUM), supervised by
Prof. Ludovic Righetti and Prof. Jeannette Bohg on dexterous manipulation.
During my PhD, I also visited Prof. Sethu Vijayakumar at University of Edinburgh and worked on robot locomotion.
NEWS
- [2024-06-16] Our paper "When and where to step: Terrain-aware real-time footstep location and timing optimization for bipedal robots" is published at Robotics and Autonomous Systems (RAS)! See the paper and video.
- [2024-05-06] Our paper "Online Multi-Contact Receding Horizon Planning via Value Function Approximation " is published at Transactions on Robotics (TRO)! See the paper and video.
SELECTED PUBLICATIONS
When and Where to Step: Terrain-Aware Real-Time Footstep Location and Timing Optimization for Bipedal Robots
Ke Wang, Zhaoyang Jacopo Hu, Peter Tisnikar, Oskar Helander, Digby Chappell, Petar Kormushev Robotics and Autonomous Systems, 2024 paper / video |
|
Online Multi-Contact Receding Horizon Planning via Value Function Approximation
Jiayi Wang, Sanghyun Kim, Teguh Santoso Lembono, Wenqian Du, Jaehyun Shim, Saeid Samadi, Ke Wang, Vladimir Ivan, Sylvain Calinon, Sethu Vijayakumar, Steve Tonneau Transactions on Robotics, 2024 paper / arxiv / video / |
|
A unified model with inertia shaping for highly dynamic jumps of legged robots
Ke Wang, Guiyang Xin, Songyan Xin, Michael Mistry, Sethu Vijayakumar, Petar Kormushev Mechatronics, 2023 paper / arxiv / video / |
Fast Online Optimization for Terrain-Blind Bipedal Robot Walking With a Decoupled Actuated SLIP Model
Ke Wang, Hengyi Fei, Petar Kormushev Frontiers in Robotics and AI, 2022 paper / arxiv / video |
|
Improved Energy Efficiency via Parallel Elastic Elements for the Straight-Legged Vertically-Compliant Robot SLIDER
Ke Wang, Roni Permana Saputra, James Paul Foster, Petar Kormushev International Conference Series on Climbing and Walking Robots and the Support Technologies for Mobile Machines (CLAWAR), 2021 Best Paper Award paper / video / |
|
Sample-efficient reinforcement learning via counterfactual-based data augmentation
Chaochao Lu, Biwei Huang, Ke Wang, José Miguel Hernández-Lobato, Kun Zhang, Bernhard Schölkopf Offline RL Workshop, NeurIPS 2020, 2020 arxiv / |
|
Design and Control of SLIDER: An Ultra-lightweight, Knee-less, Low-cost Bipedal Walking Robot
Ke Wang, David Marsh, Roni Permana Saputra, Digby Chappell, Zhonghe Jiang, Akshay Raut, Bethany Kon, Petar Kormushev IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020 (IROS 2020 presentation) paper / video / |
HONORS
- Best Paper Award,
International Conference Series on Climbing and Walking Robots and the Support Technologies for Mobile Machines (CLAWAR), 2021 - Best Poster Award,
Annual Conference Towards Autonomous Robotic Systems (TAROS), 2018
Miscellaneous
- Having lived in China, Germany and UK for many years, I am interested in exploring different cultures. I am a dad of a newborn baby!
- Outside of my research, I am also interested in hiking, swimming and basketball.