Explainable end-to-end differentiable perception for self-supervised learning in robotics

About this position

Pictus PhD Fellowship Programme

Czech Technical University in Prague – International PhD Programme (PICTUS) will recruit 8 students (see Eligibility criteria below) for a full 48-month employment contract and enroll them in a specific PhD course. Candidates should prepare their own research proposal from the List of topics for the 2nd Call .

Application form should be filled and all required documents uploaded using the dedicated electronic form.

helpdesk: pictus@cvut.cz

Guide for Applicants

Explainable end-to-end differentiable perception for self-supervised learning in robotics

Description:

Accurate perception, which enables explainable reasoning about possible outcomes of the robot-environment interaction, is essential for many fundamental capabilities, such as localization, mapping, planning or control. Despite several successful robotic's solutions, a robust perception architecture that would allow for efficient self-supervised adaptation in an unknown environment remains an open research problem. We claim that the main issues that prevent one from building such architectures are the following: (i) Black-box architectures that neglect the physical embodiment of the robot, such as deep NNs, suffer from poor generalization, weak explainability, catastrophic forgetting and the impossibility of being transferred among different robotics platforms and environments; (ii) Consequent sample-inefficient learning requires a huge number of expensive, domain-specific, human-annotated data that cannot be transferred to other domains; (iii) Resulting complex architectures have a vast number of parameters that have to be adapted/learned jointly to avoid undesirable interference among independently tuned components.

We aim to address these issues by designing grey-box, explainable, embodiment-aware, and end-to-end differentiable architectures that enable joint self-supervised adaptation from any successively incoming onboard measurements in a probabilistically consistent way.

Secondment:

R. Agishev, K. Zimmermann, V. Kubelka, M. Pecka, T. Svoboda. MonoForce: Self-supervised Learning of Physics-aware Model for Predicting Robot-terrain Interaction. IEEE-IROS 2024

V. Salansky, K. Zimmermann, T. Petricek, T. Svoboda. Pose consistency KKT-loss for weakly supervised learning of robot-terrain interaction model. IEEE Robotics and Automation Letters, 2021, Volume 6, Issue 3.

co-supervisor: Prof. Tomáš Svoboda