Burcu Kılıç

Burcu Kılıç

she/her

Undergraduate Research Assistant

Posts by Collection

publications

Learning Action Primitives in Manipulation Robots

Published in , 2025

Intelligent agents sense and act in a continuous space at the sensorimotor level. However, most of our daily tasks require manipulating a finite number of objects using a fixed set of skills, suggesting the use of perceptual and action primitives. Previous studies either learn perceptual primitives from a set of high-level actions or learn these actions from hand-coded states. In this study, we propose a neural architecture that allows simultaneous learning of action primitives together with object-level perceptual primitives from interaction data. The interaction process is guided by an active learning module that enables the search for effect-focused action parameters. The experiment results show that our model can find meaningful action primitives.

Recommended citation: B. Kilic, A. Ahmetoglu and E. Ugur, "Learning Action Primitives in Manipulation Robots," 2025 33rd Signal Processing and Communications Applications Conference (SIU), Sile, Istanbul, Turkiye, 2025, pp. 1-4, doi: 10.1109/SIU66497.2025.11111831.
Download Paper

Predictability-Based Curiosity-Guided Action Symbol Discovery

Published in , 2025

Discovering symbolic representations for skills is essential for abstract reasoning and efficient planning in robotics. Previous neuro-symbolic robotic studies mostly focused on discovering perceptual symbolic categories given a pre-defined action repertoire and generating plans with given action symbols. A truly developmental robotic system, on the other hand, should be able to discover all the abstractions required for the planning system with minimal human intervention. In this study, we propose a novel system that is designed to discover symbolic action primitives along with perceptual symbols autonomously. Our system is based on an encoder-decoder structure that takes object and action information as input and predicts the generated effect. To efficiently explore the vast continuous action parameter space, we introduce a Curiosity-Based exploration module that selects the most informative actions—the ones that maximize the entropy in the predicted effect distribution. The discovered symbolic action primitives are then used to make plans using a symbolic tree search strategy in single- and double-object manipulation tasks. We compare our model with two baselines that use different exploration strategies in different experiments. The results show that our approach can learn a diverse set of symbolic action primitives, which are effective for generating plans in order to achieve given manipulation goals.

Recommended citation: B. Kilic, A. Ahmetoglu and E. Ugur, "Predictability-Based Curiosity-Guided Action Symbol Discovery" 2025 IEEE International Conference on Development and Learning (ICDL), 2025.
Download Paper