5 accepted papers
Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these approaches holds significant promise for direct application to robotics, yet this combination has rec
Explainability is vital for establishing user trust, also in robotics. Recently, foundation models (e.g. vision-language models, VLMs) fostered a wave of embodied agents that answer arbitrary queries about their environment and their interactions with it. However, naively prompting VLMs to answer qu
Shared control enables users with motor impairments to control high-dimensional assistive robots with low-dimensional user interfaces. The challenge is to simultaneously 1) provide support for completing daily living tasks 2) enable sufficient freedom of movement to foster user empowerment 3) ensure
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for man
Assistive robots aim to help humans with impairments execute motor tasks in everyday household environments. Controlling the end-effector of such robots directly, for instance with a joystick, is often cumbersome. Shared control methods, like Shared Control Templates (SCTs) [1], have therefore been