Compositional Servoing by Recombining Demonstrations

M Argus, A Nayak, M Büchner… - … on Robotics and …, 2024 - ieeexplore.ieee.org
Learning-based manipulation policies from image inputs often show weak task transfer
capabilities. In contrast, visual servoing methods allow efficient task transfer in high …

An expansive latent planner for long-horizon visual offline reinforcement learning

R Gieselmann, FT Pokorny - RSS 2023 Workshop on Learning for …, 2023 - openreview.net
Sampling-based motion planning algorithms are highly effective in finding global paths in
geometrically-complex environments. However, classical approaches, such as RRT, are …

Synergies between Policy Learning and Sampling-based Planning

R Gieselmann - 2024 - diva-portal.org
Recent advances in artificial intelligence and machine learning have significantly impacted
the field of robotics and led to the interdisciplinary study of robot learning. These …

Aligning Planning Models with Real-World Observations

E Morgan - 2023 - search.proquest.com
While planning models are symbolic and precise, the real world is noisy and unstructured.
This work aims to bridge the gap between noise and structure by aligning visualizations of …

[PDF][PDF] An Expansive Latent Planner for Long-horizon Visual Offline RL

R Gieselmann, FT Pokorny - zt-yang.github.io
An Expansive Latent Planner for Long-horizon Visual Offline RL Page 1 An Expansive Latent
Planner for Long-horizon Visual Offline RL Robert Gieselmann (robgie@kth.se) and Florian T …