My project: Active touch and behaviour READ MORE
Research Topics: Robotics, Active touch and behavior, Event-based computation
Institution: Istituto Italiano di Tecnologia
Since my childhood, I am fascinated by the complexity and functionality of the human brain. While I was more on the technical side during my bachelor, I come closer to biology in my master. Here I came in contact with neuromorphic engineering, as a step from the technical side towards biology. To implement biological models and reduce them to the essentials, knowledge about about functionalities in biology can be won and new technical applications developed. It is very exciting for me to work as close to biology as never befor!
I chose NeuTouch, because I always wanted to be part of a great research community and get to know many engaged people. To develope solutions in a team, as an ongoing research project is a great chance to built deeper networks, friendships and learn new cool things, daily! The topic "active touch and behavior" is very exciting for me and one step further than my MCs. To work with event-based sensors is one step further towards applications in human prothetics.
Implementation of spiking tactile neural encoding on a humanoid robot, development of decoding strategies for perception and behavior generation. The robot will be a testbed to reproduce biological touch experiments (in collaboration with SISSA) of the perception of multiple stimulus properties arising from active object exploration, including light pressure, vibration, texture, lateral motion, and stretch. The task will be active exploration and modelling of an object using tactile and visual information. Visual information will be used to form an initial guess of the object shape, tactile information will be used to refine this information and complement it using features that characterize the local curvature of the object and areas that are not visible (due to occlusion). This project will use the algorithms developed within research themes 5 and 6 to classify local features from the object and machine learning models (e.g. Gaussian Processes) to model the object surface and provide an accurate shape. In the final part of the project, we will validate the surface reconstruction method in the context of object grasping, using state-of-the-art techniques that rely on object models. For comparison evaluation, we will use a dataset of objects for which accurate models are available (the Yale-CMU-Berkeley Object Data set, a dataset of object manipulation benchmarking).
Active exploration strategy based on tactile feedback for object modelling, experimental validation and benchmarking in a grasping scenario.