Project Database
This page contains the database of possible research projects for master and bachelor students in the Biorobotics Laboratory (BioRob). Visiting students are also welcome to join BioRob, but it should be noted that no funding is offered for those projects (see https://biorob.epfl.ch/students/ for instructions). To enroll for a project, please directly contact one of the assistants (directly in his/her office, by phone or by mail). Spontaneous propositions for projects are also welcome, if they are related to the research topics of BioRob, see the BioRob Research pages and the results of previous student projects.
Search filter: only projects matching the keyword Firmware are shown here. Remove filter
Amphibious robotics
Computational Neuroscience
Dynamical systems
Human-exoskeleton dynamics and control
Humanoid robotics
Miscellaneous
Mobile robotics
Modular robotics
Neuro-muscular modelling
Quadruped robotics
Quadruped robotics
A small excerpt of possible projects is listed here. Highly interested students may also propose projects, or continue an existing topic.
| 775 – Fabrication and validation of multi-axis foot contact sensors for Tegotae-based quadruped locomotion |
| Category: | master project (full-time) | |
| Keywords: | Bio-inspiration, C++, Electronics, Firmware, Quadruped Locomotion, sensor | |
| Type: | 10% theory, 50% hardware, 40% software | |
| Responsibles: |
(MED 1 1611, phone: -)
(MED 1 1611, phone: 33505) | |
| Description: | In animal locomotion, load feedback from the feet plays a critical role in coordinating inter-limb timing and achieving robust and adaptive movements. In contrast, modern quadruped robots often depend on centralized control architectures with full-state estimation, while distributed approaches such as Tegotae-based control have been limited to simplified settings, restricting their performance and versatility. The project will develop and integrate 3D force-sensitive foot sensors for a Unitree quadruped robot. Building on prior hardware designs (based on stress field sensing), custom sensors will be fabricated and embedded into the robot's feet to measure multi-axis ground reaction forces. Data-driven methods will be used to map raw sensor signals to 3D force vectors, for example through supervised learning approaches such as LSTMs. The resulting force estimates will be validated against ground-truth measurements obtained from force plates. Using these validated sensors, an existing Tegotae-based controller will be deployed, using force feedback to drive the decentralized oscillators and investigate gait transitions. The project will then extend this framework with learnable Tegotae feedback inspired from recent work, enabling adaptive and potentially omnidirectional locomotion based on multi-axis force feedback. By enriching distributed control with accurate local force sensing, this work aims to narrow the gap between decentralized, biologically inspired control and the performance currently achieved by state-of-the-art centralized approaches. Students with strong electronics background are preferred. Interested students should send their (1) transcript, (2) CV, and (3) short motivation statement for the project to louis.gevers@epfl.ch. Last edited: 28/05/2026 | |
One project found.