Terrain Recognition And Contact force Estimation Paw
Introduction
TRACEPaw is a compact and sensorized paw for legged robots, utilizing silicon deformation, an embedded micro camera, and a microphone to estimate 3D force vectors and recognize terrain types in real-time, helping the robot to adapt their locomotion strategies. This repository serves as the central hub for the TRACEPaw, containing the source code, documentation, and additional supporting materials.
Documentation
The Wiki is the primary source of documentation for TRACEPaw. It contains comprehensive information on the following topics:
- Mechanical Design & Electronics: Comprises CAD files, assembly instructions, and manufacturing guidelines, along with a comprehensive list of electronic components needed for TRACEPaw.
- Software Setup: Guide to set up the software environment for TRACEPaw, including instructions on data collection, model training & visualization, and the deployment process.
- Training and test datasets for the vision-based force estimation and audio-based terrain classification capabilities of TRACEPaw.
- Pretrained models both in Keras and TensorFlow Lite format.
Contact
Please contact us for any question: