OnlineDiscovery - AI and Robotics Badge available

Frugal learning of robot manipulation skills

  • * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

  • Date
    2 December 2025
    Timeframe
    15:00 - 16:00 CEST
    Duration
    60 minutes

    Despite significant advances in AI, robots still struggle with tasks involving physical interaction. Robots can easily beat humans at board games such as Chess or Go but struggle to skillfully move the game pieces by themselves (the part of the task that humans subconsciously succeed in). Learning manipulation skills is both hard and fascinating because the movements and behaviors to acquire are tightly connected to the physical world and to embodied forms of intelligence.

    This presentation provides an overview of representations and learning approaches to help robots acquire manipulation skills by imitation and self-refinement. The advantages of targeting a frugal learning approach are discussed, where the term “frugality” has two goals: 1) learning manipulation skills from only few demonstrations or exploration trials; and 2) learning only the components of the skill that really need to be learned.

    Toward this goal, the roles of geometry, manifolds, implicit shape representations, and distance fields are emphasized as inductive biases to facilitate human-guided manipulation skill acquisition. In addition, the presentation shows how ergodic control can provide a mathematical framework to generate exploration and coverage movement behaviors, which can be exploited by robots as a way to cope with uncertainty in sensing, proprioception, and motor control.

    Session Objectives:

    By the end of this session, participants will be able to:

    • Gain an overview of robot learning techniques (learning from demonstration, learning by exploration).
    • Identify the advantages of frugal learning from a handful of demonstrations or exploration trials.
    • Assess the important roles of representations and models to facilitate manipulation skills transfer.

    Recommended Mastery Level / Prerequisites:
    A high-level overview of robot learning techniques for manipulation skills acquisition will be showcased, with many practical examples and videos, in a presentation format that is accessible to a broad public.

  • Discovery badge available
    Showcase it on your LinkedIn profile or your professional portfolio
    Verified badge is available for CHF 10
    Learn more
    Share this session with your network
    Discover more from programme stream

    Frugal learning of robot manipulation skills

    2 December 2025 - 15:00 to 16:00

    Creative physical AI

    25 November 2025 - 17:00 to 18:00

    Robotic foundation models

    14 October 2025 - 18:00 to 19:00

    Embodied AI and Multimedia Technology Standards

    10 October 2025 - 14:00 to 18:00

    Are you sure you want to remove this speaker?