Project Database

This project has been taken

Machine learning has shown great potential for enabling robots to acquire robust and adaptive locomotion skills. For hyper-redundant robots, such as salamander-inspired robots, this remains challenging because of the high-dimensional body dynamics, the diversity of possible behaviors, and the need to integrate multimodal sensory feedback from both terrestrial and aquatic environments.

This project is an extension of a previous project, in which we will keep exploring learning-based methods for improving salamander robot locomotion in complex amphibious environments. Possible directions include sensor fusion, maneuvering, transition, sim-real transfer, etc. A key goal will be to evaluate whether biological/physical priors can improve learning efficiency, robustness, and smooth transitions between behaviors.

The project is suitable for a highly self-motivated student with complete project experience in machine learning. Familiarity with MuJoCo MJX or other physics simulators is expected. Experience with CPGs, signal processing, reinforcement learning, or sensor-based control will be helpful.

Students who are interested in this project shall send the following materials to the assistant: (1) resume, (2) transcript showing relevant courses and grades, and (3) other materials that can demonstrate their skills and project experience (such as videos, slides, Git repositories, etc.).

Why do horses and and camels both walk at slow speeds and gallop at fast speeds, but at intermediate speeds horses prefer to trot while camels pace? While gait transitions have been well studied for a given morphology, these models rarely explain when and why animals prefer different or gaits despite being quite similar, or the same gaits despite having very different morphologies. This project tackles this question through the lens of reinforcement learning (RL), with a focus on the role of entrainment between an internal oscillator model and the mechanical dynamics, i.e the morphology. You will explore both top-down and bottom-up coupling mechanisms, unconventional reward functions such as viability measures, and benchmark these approaches across different morphological parameters (e.g length-to-height and width-to-height ratios, mass). Stretch goals can include evaluating the role of active exploration in a hierarchical RL setup, exploring sprawling or bipedal morphologies, changing morphology during learning (e.g. growth), or you may propose something in discussion with the supervisors.

NOTE: this is a collaboration project, to be conducted at Cornell University, USA. To apply, e-mail Steve Heim stating why you are interested in this project (brief, 1-2 sentences each), and attach your CV and transcript.

Animals display a rich diversity of behaviors in natural environments, but only a small set of them have been well studied and simplified into template gaits. Recent advances in imitation learning have enabled quadruped and humanoid robots to reproduce complex animal and human motions, but these approaches have been less explored for amphibious robots that must coordinate body, limbs, and environmental interactions across water and land.

In this project, we will work on the recordings of real salamanders in a vivarium with various terrains. We will extract multi-terrain locomotion behaviors from the collected motion data. Then we will investigate how diverse salamander behaviors can be transferred to simplified salamander models or salamander-inspired robots.

The student is expected to be familiar with Python programming, signal processing, kinematics, and imitation learning. Experience with dimensionality reduction, MuJoCo simulation, and CPGs is highly recommended.

Students who are interested in this project shall send the following materials to the assistants: (1) resume, (2) transcript showing relevant courses and grades, and (3) other materials that can demonstrate their skills and project experience (such as videos, slides, Git repositories, etc.).