PI: Farnaz Adib Yaghmaie, Linköping University
co-PI: Yiannis Karayiannidis, Lund University
Mobile manipulation, i.e., manipulation tasks performed by robots that can move through and interact with large, unconstrained environments, requires learning methods that go beyond fixed workspaces. This proposal aims to investigate and develop learning-based solutions for mobile manipulation that leverage both expert demonstrations and experiential learning. Learning from expert data offers a fast, safe, and efficient pathway to skill acquisition. In parallel, Reinforcement Learning (RL) facilitates systematic exploration and adaptation for manipulation planning. By integrating the strengths of expert-driven learning and RL-based experience, this research seeks to create robust, data-efficient learning strategies for mobile manipulation that generalize across diverse operational environments and transfer effectively to a wide range of real-world robotic applications, inherently ensuring dual use.
Project number: G1