CoCap: Coordinated motion Capture for multi-actor scenes in outdoor environments

IROS Workshop 2024

Aditya Rauniyar1, Micah Corah2, Sebastian Scherer1,
Carnegie Mellon University1, Colorado School of Mines2
Paper arXiv
CoCap: Coordinated motion Capture for multi-actor scenes in outdoor environments

Coverage optimization on dynamic actors with flying cameras in an occlusion-aware and obstacle-clustered environment where camera extrinsic positions across robots are negotiated

Abstract

Motion capture has become increasingly important, not only in computer animation but also in emerging fields like virtual reality, bioinformatics, and humanoid training. Capturing outdoor environments offers extended horizon scenes but introduces challenges with occlusions and obstacles. Recent approaches using multi-drone systems to capture multiple actor scenes often fail to account for multi-view consistency and reasoning across cameras in cluttered environments. Coordinated motion Capture (CoCap), inspired by Conflict-Based Search (CBS), addresses this issue by coordinating view planning to ensure multi-view reasoning during conflicts. In scenarios with high occlusions and obstacles, where the likelihood of inter- robot collisions increases, CoCap demonstrates performance that approaches the ideal outcomes of unconstrained planning, out- performing existing sequential planning methods. Additionally, CoCap offers a single-robot view search approach for real-time applications in dense environments.

Need for Enhancing Motion Capture Techniques for Outdoor Settings.

indoor motion capture

Motion Capture of multi-actor scenes for virtual production

(Figure referenced from Optitrack)

Cyclist

Outdoor scenes provide long horizon motion capture sequence

(Figure referenced from Optitrack)

Humanoid

Motion capture provides high quality data for humanoid training

(Harrison Schell from madevisual.co)

Key factors in high-quality multi-actor motion capture.

multi-view-capture

Multi-view capture

occlusion-reasoning

Occlusion reasoning

Collision-Avoidance-of-Remotely-Piloted-UAV

Obstacle Avoidance

multi-person coverage

Multi-person coverage

(Figure referenced from paperswithcode.com)

Qualitative comparison of different planning methods.

Qualitative comparison of different planning methods

Reward Comparison:

Scenarios

2.5D Map

Corridor

2.5D Map for Corridor

Total actors: 2

Total horizon: 8

#Robots: 2

Reward Chart for Corridor

Bottleneck

2.5D Map for Bottleneck

Total actors: 4

Total horizon: 12

#Robots: 4

Reward Chart for Bottleneck

BibTeX


        @misc{rauniyar2024cocapcoordinatedmotioncapture,
              title={CoCap: Coordinated motion Capture for multi-actor scenes in outdoor environments}, 
              author={Aditya Rauniyar and Micah Corah and Sebastian Scherer},
              year={2024},
              eprint={2412.20695},
              archivePrefix={arXiv},
              primaryClass={cs.RO},
              url={https://arxiv.org/abs/2412.20695}, 
        }