A Hierarchical Framework for Long Horizon Planning of Object-Contact Trajectories

Aceituno, Bernardo; Rodríguez, Alberto

doi:10.1109/iros47612.2022.9981862

Cited by 2 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We introduce a more optimized search structure, addressing three key issues: no mechanism to optimize for any reward, random sampling for robot contact planning, and an entangled configuration space of the object and the robot that results in many redundant searches. We introduce hierarchical search to decompose the space of object motion and robot contacts [19], [20]. Unlike previous approaches using contact states, which can have the combinatoric explosion for 3D cases, our method leverages contact modes and efficient robot contact search, extending the application from 2D polyhedrons to 3D meshes.…”

Section: Related Work a Dexterous Manipulation Planningmentioning

confidence: 99%

Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration

Cheng,

Patil,

Temel

et al. 2024

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Planning robot dexterity is challenging due to the non-smoothness introduced by contacts, intricate fine motions, and ever-changing scenarios. We present a hierarchical planning framework for dexterous robotic manipulation (HiDex). This framework explores in-hand and extrinsic dexterity by leveraging contacts. It generates rigid-body motions and complex contact sequences. Our framework is based on Monte-Carlo Tree Search (MCTS) and has three levels: 1) planning object motions and environment contact modes; 2) planning robot contacts; 3) path evaluation and control optimization. This framework offers two main advantages. First, it allows efficient global reasoning over high-dimensional complex space created by contacts. It solves a diverse set of manipulation tasks that require dexterity, both intrinsic (using the fingers) and extrinsic (also using the environment), mostly in seconds. Second, our framework allows the incorporation of expert knowledge and customizable setups in task mechanics and models. It requires minor modifications to accommodate different scenarios and robots. Hence, it provides a flexible and generalizable solution for various manipulation tasks. As examples, we analyze the results on 7 hand configurations and 15 scenarios. We demonstrate 8 tasks on two robot platforms.

show abstract

Section: Related Work a Dexterous Manipulation Planningmentioning

confidence: 99%

Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration

Cheng,

Patil,

Temel

et al. 2024

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Prior work has investigated how the hierarchical nature of a task can facilitate long-horizon task completion [2,35,38]. Breaking up a long-horizon task hierarchically and abstracting the task components into repurposable sub-tasks reduces planning depth and allows for faster planning [24,29].…”

Section: Hierarchical Task Representationsmentioning

confidence: 99%

Investigating the Impact of Experience on a User's Ability to Perform Hierarchical Abstraction

Moorman,

Gopalan,

Singh

et al. 2023

Robotics: Science and Systems XIX

View full text Add to dashboard Cite

The field of Learning from Demonstration enables end-users, who are not robotics experts, to shape robot behavior. However, using human demonstrations to teach robots to solve long-horizon problems by leveraging the hierarchical structure of the task is still an unsolved problem. Prior work has yet to show that human users can provide sufficient demonstrations in novel domains without showing the demonstrators explicit teaching strategies for each domain. In this work, we investigate whether non-expert demonstrators can generalize robot teaching strategies to provide necessary and sufficient demonstrations to robots zero-shot in novel domains. We find that increasing participant experience with providing demonstrations improves their demonstration's degree of sub-task abstraction (p < .001), teaching efficiency (p < .001), and sub-task redundancy (p < .05) in novel domains, allowing generalization in robot teaching. Our findings demonstrate for the first time that non-expert demonstrators can transfer knowledge from a series of training experiences to novel domains without the need for explicit instruction, such that they can provide necessary and sufficient demonstrations when programming robots to complete task and motion planning problems.

show abstract

A Hierarchical Framework for Long Horizon Planning of Object-Contact Trajectories

Cited by 2 publications

References 25 publications

Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration

Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration

Investigating the Impact of Experience on a User's Ability to Perform Hierarchical Abstraction

Contact Info

Product

Resources

About