Chao Ni

I work on machine learning aspect of robotics and am building humanoids at Hexagon.

I received my master degree in robotics at ETH Zurich and my bachelor degree in mathematical mechanics at Peking University. I also hold on bachelor degree in economics at Peking University.

I like triathlon and outdoor activities. I am also a casual photographer.

Email  /  Twitter  /  Linkedin  /  Github

Here is a few projects I have worked on.

Leveraging demonstrations from MPC expert, the robot learns to walk over structured terrains.

By learning the distribution of optimal samples given a local map, sampling-based exploration planning can be done efficiently.

Here is a list of my past projects, including course projects and unpublished work.

Learning to navigate in the forest using only a monocular event camera.

We create a motion primitive library with trajectories generated by modulizable optimizers and use Model Predictive Control to track the trajectory.

Inverse Kinamtics solver for the hexpod robot is implemented, simple PD feedback is used for torque control. An obstacle avoidance algorithm is used to achieve navigation tasks.

We extract effective representation from the multi-sensory robotics data by self-supervised synchronization and use the latent representation for downstream RL tasks.

We quotient out the temporal fluctuations of the video and insert a preprocessing frame selection layer in the action recognition learning framework.

Here is a list of my personal literature reviews and pointers to some of my passions.

A literature review on Robot Learning: robot learning