On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks

MN Qureshi, B Eisner, D Held - arXiv preprint arXiv:2401.01993, 2024 - arxiv.org
While solving complex manipulation tasks, manipulation policies often need to learn a set of
diverse skills to accomplish these tasks. The set of skills is often quite multimodal-each one …

Disentangling Planning and Control for Non-Prehensile Tabletop Manipulation

VR Mandadi, K Saha, D Guhathakurta… - 2023 IEEE 19th …, 2023 - ieeexplore.ieee.org
Manipulating a target object using non-prehensile actions presents a complex problem that
requires addressing multiple constraints, such as finding collision-free trajectories, modeling …

[PDF][PDF] Discrete and Continuous Trajectory Optimization Methods for Complex Robot Systems

D Guhathakurta - 2023 - cdn.iiit.ac.in
Path planning for autonomous systems is a fundamental problem in robotics, especially
when the task assigned to a robot is heavily dependent on the motion of one or more of its …