Emre Ugur from INVERSE partner Boğaziçi University was invited to talk at Learning Effective Abstractions for Planning (LEAP) Workshop at the Conference on Robot Learning CORL 2025. CORL 2025 took place on the 27th of September in Seoul, South Korea.
Emre Ugur invited to talk at Learning Effective Abstractions for Planning (LEAP) Workshop
As one of three invited speakers, Emre gave a talk titled “DeepSym: A Neuro-symbolic Approach for Symbol Emergence and Planning” at the Learning Effective Abstractions for Planning (LEAP) Workshop. The talk centered on abstract reasoning and how robots could achieve abstract reasoning on their own. Abstract reasoning is among the most essential characteristics of high-level intelligence that distinguish humans from other animals. If the robots can achieve abstract reasoning on their own, they can perform new tasks in completely novel environments by updating their cognitive skills or by discovering new symbols and rules.
A novel general framework: DeepSym
In his talk, he proposed a novel general framework, DeepSym, which discovers interaction grounded, discrete object, action and effect categories and builds probabilistic rules for non-trivial action planning. In DeepSym, the robot interacts with objects using an initial action repertoire and observes the effects it can create in the environment. To form interaction-grounded object, action, effect, and relational categories, they employ a binary bottleneck layer in a predictive, deep encoder-decoder network that takes the image of the scene and the action parameters as input and generates the resulting effects in the scene in pixel coordinates. The knowledge represented by the neural network is distilled into rules and represented in the Probabilistic Planning Domain Definition Language (PPDDL), allowing off-the-shelf planners to operate on the knowledge extracted from the sensorimotor experience of the robot.
Congratulations to Emre Ugur for this talk!