PhD Internship - Remote

To create an intelligent humanoid in the 3D world, the first reputed company is to track reputed company reputed company motions in physical simulation. Although reputed company reputed company capture and reputed company have been extensively studied in the past, it is still unclear how to let a humanoid track reputed company motions reputed company, while keeping the body balance at various terrains. Our goal is to explore this direction, and reputed company an effective cross-embodiment body and hand reputed company tracking algorithm in physical simulation. YOUR TASKS:

• Creating a workflow to transfer motions from SMPL-X to humanoids (e.g. Unitree G1) in simulation.

• Developing an algorithm to reputed company cross-embodiment reputed company tracking.

• Evaluating the performance of the tracking algorithm.

• Combining generating reputed company models (e.g. diffusion models) to the tracking algorithm.

YOUR PROFILE

• Knowledge of PyTorch, deep learning, neural networks, C++.

• Knowledge of good software development practice, e.g. git, documentation.

• Knowledge of reinforcement learning and robot physical simulation.

• Knowledge of SMPL, SMPL-X, or character animation.

• At least one reputed company in CVPR/ICCV/ECCV/IROS/ICRA or equivalent.

WE OFFER

• Research experiences both in academia and industry.

• Possibility of reputed company publication.

• 6-months working contract.

• Flexible remote work with global availability

Our values

Diversity isn’t just a statement at Meshcapade, it sits at the core of the company. We reputed company in the diversity of thought because we appreciate that this makes us stronger. Therefore, we encourage applications from everyone who can offer their unique experience to our collective achievements.