Self-Supervised Robot Learning for Spatial Perception

Decanato - Facoltà di scienze informatiche

Data: 11 Dicembre 2023 / 15:30 - 18:00

USI East Campus / online

You are cordially invited to attend the PhD Dissertation Defence of Mirko Nava on Monday 11 December 2023 at 15:30 in room D0.02 (USI East Campus) and online.

Nowadays, deep learning techniques are ubiquitous for robot perception tasks, thanks to their ability to recognize complex patterns and handle high-dimensional data. Crucial to the success of a robot learning approach is the amount and quality of labeled training data. Collecting a large amount of labeled training data requires much effort and resources. In this dissertation, we discuss and propose novel approaches for self-supervised robot learning, where the robot autonomously collects data and uses it to supervise the training or fine-tuning of a deep learning model. Specifically, we focus on spatial perception tasks, which entail the robot’s ability to interpret complex visual data to estimate the geometrical properties of the environment, including the location of humans, obstacles, robots, and other relevant objects. Self-supervised robot learning is compelling because it allows the robot to collect large quantities of training data without requiring the involvement of humans; in fact, the robot may collect data in all the environments it can explore. The model is trained on the task at hand using the collected data; in addition, the model may be asked to solve an auxiliary task, named pretext, to learn better features and improve its performance. By introducing the pretext task, we limit the need for labeled data required to achieve an adequate level of performance. We describe here our contributions to the field and present three potential research avenues for alleviating the challenges associated with large-scale data collection and for the improvement of perception models.

Dissertation Committee:
- Prof. Luca Maria Gambardella, Università della Svizzera italiana, Switzerland (Research Advisor)
- Prof. Alessandro Giusti, IDSIA USI-SUPSI, Switzerland (Research co-Advisor)
- Prof. Cesare Alippi, Università della Svizzera italiana, Switzerland (Internal Member)
- Prof. Piotr Krzysztof Didyk, Università della Svizzera italiana, Switzerland (Internal Member)
- Prof. Cesar Cadena, ETHZ, Switzerland (External Member)
- Prof. Matteo Matteucci, Politecnico di Milano, Italy (External Member)