Benchmarking the utility of maps of dynamics for human-aware motion planning
Robots operating with humans in highly dynamic environments need not only react to moving persons and objects but also to anticipate and adhere to patterns of motion of dynamic agents in their environment. Currently, robotic systems use information about dynamics locally, through tracking and predic...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2022.916153/full |
| _version_ | 1811332479057920000 |
|---|---|
| author | Chittaranjan Srinivas Swaminathan Tomasz Piotr Kucner Martin Magnusson Luigi Palmieri Sergi Molina Anna Mannucci Federico Pecora Achim J. Lilienthal |
| author_facet | Chittaranjan Srinivas Swaminathan Tomasz Piotr Kucner Martin Magnusson Luigi Palmieri Sergi Molina Anna Mannucci Federico Pecora Achim J. Lilienthal |
| author_sort | Chittaranjan Srinivas Swaminathan |
| collection | DOAJ |
| description | Robots operating with humans in highly dynamic environments need not only react to moving persons and objects but also to anticipate and adhere to patterns of motion of dynamic agents in their environment. Currently, robotic systems use information about dynamics locally, through tracking and predicting motion within their direct perceptual range. This limits robots to reactive response to observed motion and to short-term predictions in their immediate vicinity. In this paper, we explore how maps of dynamics (MoDs) that provide information about motion patterns outside of the direct perceptual range of the robot can be used in motion planning to improve the behaviour of a robot in a dynamic environment. We formulate cost functions for four MoD representations to be used in any optimizing motion planning framework. Further, to evaluate the performance gain through using MoDs in motion planning, we design objective metrics, and we introduce a simulation framework for rapid benchmarking. We find that planners that utilize MoDs waste less time waiting for pedestrians, compared to planners that use geometric information alone. In particular, planners utilizing both intensity (proportion of observations at a grid cell where a dynamic entity was detected) and direction information have better task execution efficiency. |
| first_indexed | 2024-04-13T16:36:40Z |
| format | Article |
| id | doaj.art-e634c73ce4d94da7a4884c869946be52 |
| institution | Directory Open Access Journal |
| issn | 2296-9144 |
| language | English |
| last_indexed | 2024-04-13T16:36:40Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj.art-e634c73ce4d94da7a4884c869946be522022-12-22T02:39:24ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442022-11-01910.3389/frobt.2022.916153916153Benchmarking the utility of maps of dynamics for human-aware motion planningChittaranjan Srinivas Swaminathan0Tomasz Piotr Kucner1Martin Magnusson2Luigi Palmieri3Sergi Molina4Anna Mannucci5Federico Pecora6Achim J. Lilienthal7AASS Lab, School of Science and Technology, Örebro University, Örebro, SwedenFinnish Centre for Artificial Intelligence (FCAI), Department of Electrical Engineering and Automation, Aalto University, Espoo, FinlandAASS Lab, School of Science and Technology, Örebro University, Örebro, SwedenRobert Bosch GmbH Corporate Research, Stuttgart, GermanyLincoln Centre for Autonomous Systems, School of Computer Science, University of Lincoln, Lincoln, United KingdomAASS Lab, School of Science and Technology, Örebro University, Örebro, SwedenAASS Lab, School of Science and Technology, Örebro University, Örebro, SwedenAASS Lab, School of Science and Technology, Örebro University, Örebro, SwedenRobots operating with humans in highly dynamic environments need not only react to moving persons and objects but also to anticipate and adhere to patterns of motion of dynamic agents in their environment. Currently, robotic systems use information about dynamics locally, through tracking and predicting motion within their direct perceptual range. This limits robots to reactive response to observed motion and to short-term predictions in their immediate vicinity. In this paper, we explore how maps of dynamics (MoDs) that provide information about motion patterns outside of the direct perceptual range of the robot can be used in motion planning to improve the behaviour of a robot in a dynamic environment. We formulate cost functions for four MoD representations to be used in any optimizing motion planning framework. Further, to evaluate the performance gain through using MoDs in motion planning, we design objective metrics, and we introduce a simulation framework for rapid benchmarking. We find that planners that utilize MoDs waste less time waiting for pedestrians, compared to planners that use geometric information alone. In particular, planners utilizing both intensity (proportion of observations at a grid cell where a dynamic entity was detected) and direction information have better task execution efficiency.https://www.frontiersin.org/articles/10.3389/frobt.2022.916153/fullhuman-aware motion planningmaps of dynamicsdynamic environmentsbenchmarkinghuman-populated environmentsATC |
| spellingShingle | Chittaranjan Srinivas Swaminathan Tomasz Piotr Kucner Martin Magnusson Luigi Palmieri Sergi Molina Anna Mannucci Federico Pecora Achim J. Lilienthal Benchmarking the utility of maps of dynamics for human-aware motion planning Frontiers in Robotics and AI human-aware motion planning maps of dynamics dynamic environments benchmarking human-populated environments ATC |
| title | Benchmarking the utility of maps of dynamics for human-aware motion planning |
| title_full | Benchmarking the utility of maps of dynamics for human-aware motion planning |
| title_fullStr | Benchmarking the utility of maps of dynamics for human-aware motion planning |
| title_full_unstemmed | Benchmarking the utility of maps of dynamics for human-aware motion planning |
| title_short | Benchmarking the utility of maps of dynamics for human-aware motion planning |
| title_sort | benchmarking the utility of maps of dynamics for human aware motion planning |
| topic | human-aware motion planning maps of dynamics dynamic environments benchmarking human-populated environments ATC |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2022.916153/full |
| work_keys_str_mv | AT chittaranjansrinivasswaminathan benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning AT tomaszpiotrkucner benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning AT martinmagnusson benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning AT luigipalmieri benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning AT sergimolina benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning AT annamannucci benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning AT federicopecora benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning AT achimjlilienthal benchmarkingtheutilityofmapsofdynamicsforhumanawaremotionplanning |