Many quadruped robots use simple ball feet, while animals usually have complex foot structures. Some studies have tried designing more complex actuated or adaptive feet for quadruped robots. However, few have systematically investigated the benefits of such feet when they are integrated into the robot, especially for the sprawling-type quadrupeds. The lack of understanding also exists in animal locomotion because of the complexity and small dimensions of the structure.

To start understanding the role of biomimetic foot structures, we have had several projects designing passive feet for our salamander-inspired robots. This project aims to further extend the results by improving the design and more systematically collecting data in different environments.

The semester student will: (1) improve the design of the feet based on previous studies, (2) perform systematic tests in different environments, and (3) analyze the results. The student is expected to be experienced in mechanical design and manufacturing, Python programming, and robot kinematics. Knowledge of robot dynamics and elastic rod theories is also helpful.

If the student aims to finish a master's thesis based on this project, the student needs to additionally finish one of the following tasks: (1) model the passive feet dynamics from first principles or neural networks, (2) develop novel sensors to monitor the states of the feet, (3) design novel structures to integrate the design with the entire leg.

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 your skills and project experience (such as videos, slides, Git repositories, etc.).

In this project, the student will work closely with the other team members to develop data collection pipelines during the experiments of a sensorized amphibious robot and, optionally, use them to collect and analyze experimental data. Specifically, the student needs to:

• Build a multi-camera system for tracking 3-D kinematics of the robots, ideally in real time. The system is expected to work in both indoor and outdoor experiments. We already have a few working setups, and the student needs to replicate them using new hardware, calibrate the system, and integrate it with ROS2.
• Synchronize data collected from multiple resources: cameras, force sensors, motors, etc.
• Visualize the data collected in RViz, Blender, or other 3D visualizers.
• Help collect experimental data.
• (For master project only) Help analyze data or use learning algorithms to find underlying patterns.

The student is expected to be familiar with programming in C/C++ and Python, have experience using ROS2, and have learned about robot kinematics. Experience with Docker, Linux kernel, communication protocols, and computer vision algorithms would be a bonus.

The student who is 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, code repositories, etc.).

This project has been taken.

Pleurobot is a salamander-inspired robot that is capable of moving in and transitioning between terrestrial and aquatic environments. Some research projects in our lab have demonstrated the effectiveness of vision-guided or human-controlled locomotion transition strategies. However, the present Pleurobot is unable to use similar strategies robustly, especially in outdoor environments, because of lacking vision systems or robust wireless controllers.

In this project, the student will need to add vision systems (e.g., RGB-D camera) for Pleurobot that can operate in amphibious environments. In addition, a robust radio controller is needed to operate the robot in outdoor environments. Alternatively, the student can choose to implement algorithms for the vision system for recognizing terrain and obstacles in real-time. Both systems need to be integrated into the ROS 2 controller running on the onboard computer. The major challenges include the requirements for waterproofing, the limited space for electronics, and the fusion of multiple sensory systems in an embedded system.

The student is expected to have a solid background in circuit design for embedded systems, firmware programming, and familiarity with ROS 2. The student who is interested in this project could send his/her transcript, CV, and materials that can demonstrate his/her past project experience to qiyuan.fu@epfl.ch.

This project has been taken

Robots can be useful tools to study animal locomotion in physical environments. However, present robot actuators can barely reach the high power density of animal muscles. In addition, the differences in the morphologies of motors and muscles lead to differences in the geometry and dynamics between robots and animals. Cable-driven mechanisms offer a promising way to bridge the gap, because they enable more flexible placement of actuators and integration of mechanisms similar to animal musculoskeletal systems.

In this project, the student will refine the design of a cable-driven leg for our salamander robots. The objectives are to reduce the weight and rotational inertia, reduce the size, and increase output torque along different axes. The design needs to be rigorously tested in a standalone setup and on the real robot.

In nature, animals have many compliant structures that benefit their locomotion. For example, compliant foot/leg structures help adapt to uneven terrain or negotiate obstacles, flexible tails allow efficient undulatory swimming, and muscle-tendon structures help absorb shock and reduce energy loss. Similar compliant structures may benefit salamander-inspired robots as well.

In this study, the student will try simulating compliant structures (the feet of the robot) in Mujoco and optimizing the design. To bridge the sim-to-real gap, the student will first work with other lab members to perform experiments to measure the mechanical properties of a few simple compliant structures. Then, the student needs to simulate these experiments using the flexcomp plugin of Mujoco or theoretical solid mechanics models and tune the simulation models to match the dynamical response in simulation with the experiments. Afterward, the student needs to optimize the design parameters of the compliant structures in simulation to improve the locomotion performance of the robot while maintaining a small sim-to-real gap. Finally, prototypes of the optimal design will be tested on the physical robot to verify the results.

The student is thus required to be familiar with Python programming, physics engines (preferably Mujoco), and optimization/learning algorithms. The student should also have basic mechanical design abilities to design models and perform experiments. Students who have taken the Computational Motor Control course or have experience with data-driven design and solid mechanics would also be preferred.

The student who is 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 your skills and project experience (such as videos, slides, Git repositories, etc.).

NOTE: this is a collaboration project, to be conducted at Cornell University, USA.

Last edited: 02/12/2025

This project will done in collaboration with James Hermus at IDIAP.

• Drop Jump
• Squat Jump
• Velocity-Based Training

• Data Collection: Acquire athlete performance data in a motion analysis lab under standardized conditions.
• Data Preprocessing: Clean, structure, and prepare the dataset for analysis.
• Statistical Analysis: Apply statistical methods to assess Optizone’s algorithms against the gold-standard reference system

• Estimating workload metrics (e.g., jump count, movement intensity, acceleration patterns)
• Classifying basketball actions based on IMU-derived motion signatures.
Video recordings will be used solely to verify and annotate the IMU data, serving as a ground truth for validating the accuracy of the developed classification and workload estimation models. This project will result in a practical and sport-specific tool for coaches, trainers, and sports scientists to monitor performance and manage training loads using compact wearable technology, without relying on complex camera setups or external tracking systems. Data collection is a part of project

Last edited: 29/08/2025

Mobile robots often communicate over the 2.4 GHz band using standard off-the-shelf technologies as WiFi or Bluetooth, or sometimes custom radio protocols either on the 2.4 GHz or 868 MHz ISM bands, both on the UHF part of the radio spectrum. This project aims at evaluating the possibility of using the 169.4 MHz band (VHF) for controlling robots and obtaining telemetry, as it might give much better results in terms of range and transmission through obstacles or water, even if the available bandwidth is much more restricted.

The project involves:

• Identifying an appropriate RF module/chip
• Creating a printed circuit if necessary
• Using a microcontroller to control the RF module and obtain bidirectional communication
• Experiments for range in open air, through obstacles and underwater

Requirements: experience with digital electronics and basic understanding of radio communications and related concepts (e.g. transmission lines, antennas). Previous experience with radio frequency and/or PCB design is a plus.