activity
20242026
collaborators
Showing cs.ROShow all

10 papers · 1 filter

cs.RO2026

PEEL: Parallel Extraction for Long-Horizon Disassembly Planning via Scale-Invariant Sampling

Servet B. Bayraktar, Andreas Orthey, Zachary Kingston +1

Long-horizon multi-part object disassembly requires robots to compute feasible sequences of collision-free removal motions, even in the presence of tight, narrow escape corridors.…

cs.RO2026

Coordinated Multi-Robot Disassembly for Makespan Optimization of Large-Scale Assemblies

Niklas Hargus, Andreas Orthey, Marc Toussaint

Multi-robot task and motion planning for disassembly tasks requires robots to operate in confined workspaces while coordinating their motions with other robots. To tackle this prob…

cs.RO2026

PhyRoGen: Synthetic Generation of Physical Robot Manipulation Puzzles Using Procedural Content Generation

Lennart Julian Droß, Andreas Orthey, Marc Toussaint

Robot manipulation of physical puzzles is important for automatic assembly and disassembly tasks. However, to enable robots to solve physical puzzles, manipulation skills need to b…

cs.RO2026

Optimizing Trajectory-Trees in Belief Space: An Application from Model Predictive Control to Task and Motion Planning

Camille Phiquepal, Marc Toussaint

This paper explores the benefits of computing arborescent trajectories (trajectory-trees) instead of commonly used sequential trajectories for partially observable robotic planning…

cs.RO2026

Scale-Invariant Sampling in Multi-Arm Bandit Motion Planning for Object Extraction

Servet B. Bayraktar, Andreas Orthey, Marc Toussaint

Object extraction tasks often occur in disassembly problems, where bolts, screws, or pins have to be removed from tight, narrow spaces. In such problems, the distance to the enviro…

cs.RO2026

Stability-Guided Exploration for Diverse Motion Generation

Eckart Cobo-Briesewitz, Tilman Burghoff, Denis Shcherba +2

Scaling up datasets is highly effective in improving the performance of deep learning models, including in the field of robot learning. However, data collection still proves to be…