11 papers
One Body, Two Minds: Variable Autonomy Approach for a Co-embodied Robotic Hand
Piotr Koczy, Yuchong Zhang, Danica Kragic +1
Assistive robotic systems face a fundamental trade-off: fully autonomous systems lack user agency, while fully user-controlled systems demand continuous cognitive effort. Existing…
On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning
Thomas Lips, Marco Moletta, Michael C. Welle +2
RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representations to improve generalization…
Gesture First, LLM-Assisted Voice Complement: Exploring Multimodal Robot 'Puppeteer' Teleoperation Via Virtual Counterpart in Augmented Reality
Yuchong Zhang, Bastian Orthmann, Shichen Ji +3
Robot teleoperation via augmented reality (AR) offers a promising path toward more intuitive human-robot interaction (HRI). We present a head-mounted AR 'puppeteer' system in which…
Real-Time Operator Takeover for Visuomotor Diffusion Policy Training
Marco Moletta, Michael C. Welle, Nils Ingelhag +2
We present a Real-Time Operator Takeover (RTOT) paradigm that enables operators to seamlessly take control of a live visuomotor diffusion policy, guiding the system back to desirab…
Preference Aligned Visuomotor Diffusion Policies for Deformable Object Manipulation
Marco Moletta, Michael C. Welle, Danica Kragic
Humans naturally develop preferences for how manipulation tasks should be performed, which are often subtle, personal, and difficult to articulate. Although it is important for rob…
Hybrid-Diffusion Models: Combining Open-loop Routines with Visuomotor Diffusion Policies
Jonne Van Haastregt, Bastian Orthmann, Michael C. Welle +2
Despite the fact that visuomotor-based policies obtained via imitation learning demonstrate good performances in complex manipulation tasks, they usually struggle to achieve the sa…