Dcruz, Julian GeraldMahoney, SamChua, Jia YunSoukhabandith, AdoundethMugabe, JohnGuo, WeisiArana-Catania, Miguel2025-07-032025-07-032024-10-29Dcruz JG, Mahoney S, Chua JY, et al., (2024) Causal reinforcement learning for optimisation of robot dynamics in unknown environments. In: 2024 IEEE International Smart Cities Conference (ISC2), 29 October 2024 - 1 November 2024, Pattaya, Thailand979-8-3503-6432-32687-8852https://doi.org/10.1109/isc260477.2024.11004233https://dspace.lib.cranfield.ac.uk/handle/1826/24131Autonomous operations of robots in unknown environments are challenging due to the lack of knowledge of the dynamics of the interactions, such as the objects' movability. This work introduces a novel Causal Reinforcement Learning approach to enhancing robotics operations and applies it to an urban search and rescue (SAR) scenario. Our proposed machine learning architecture enables robots to learn the causal relationships between the visual characteristics of the objects, such as texture and shape, and the objects’ dynamics upon interaction, such as their movability, significantly improving their decision-making processes. We conducted causal discovery and RL experiments demonstrating the Causal RL’s superior performance, showing a notable reduction in learning times by over 24.5% in complex situations, compared to non-causal models.enAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/46 Information and Computing Sciences4602 Artificial Intelligence4611 Machine LearningMachine Learning and Artificial IntelligenceBasic Behavioral and Social ScienceBehavioral and Social ScienceCausal LearningReinforcement LearningAutonomous SystemsRoboticsCausal reinforcement learning for optimisation of robot dynamics in unknown environmentsConference paper979-8-3503-6431-62687-8860673380