Closed-Loop Next-Best-View Planning for Target-Driven Grasping


METADATA ONLY
Loading...

Date

2022

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Picking a specific object from clutter is an essential component of many manipulation tasks. Partial observations often require the robot to collect additional views of the scene before attempting a grasp. This paper proposes a closed-loop next-best-view planner that drives exploration based on occluded object parts. By continuously predicting grasps from an up-to-date scene reconstruction, our policy can decide online to finalize a grasp execution or to adapt the robot's trajectory for further exploration. We show that our reactive approach decreases execution times without loss of grasp success rates compared to common camera placements and handles situations where the fixed baselines fail. Video and code are available at https://github.com/ethz-asl/active_grasp.

Publication status

published

Editor

Book title

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

Journal / series

Volume

Pages / Article No.

1411 - 1416

Publisher

IEEE

Event

35th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Robot vision systems; Grasping; Cameras; Search problems; Robustness; Trajectory; Planning

Organisational unit

03737 - Siegwart, Roland Y. / Siegwart, Roland Y. check_circle

Notes

Funding

Related publications and datasets