File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/LRA.2017.2651371
- Scopus: eid_2-s2.0-85042294932
- WOS: WOS:000413736600037
Supplementary
- Citations:
- Appears in Collections:
Article: Deep-learned collision avoidance policy for distributed multiagent navigation
Title | Deep-learned collision avoidance policy for distributed multiagent navigation |
---|---|
Authors | |
Keywords | Collision avoidance deep learning distributed robot systems multi-agent navigation |
Issue Date | 2017 |
Citation | IEEE Robotics and Automation Letters, 2017, v. 2, n. 2, p. 656-663 How to Cite? |
Abstract | High-speed, low-latency obstacle avoidance that is insensitive to sensor noise is essential for enabling multiple decentralized robots to function reliably in cluttered and dynamic environments. While other distributed multiagent collision avoidance systems exist, these systems require online geometric optimization where tedious parameter tuning and perfect sensing are necessary. We present a novel end-to-end framework to generate reactive collision avoidance policy for efficient distributed multiagent navigation. Our method formulates an agent's navigation strategy as a deep neural network mapping from the observed noisy sensor measurements to the agent's steering commands in terms of movement velocity. We train the network on a large number of frames of collision avoidance data collected by repeatedly running a multiagent simulator with different parameter settings. We validate the learned deep neural network policy in a set of simulated and real scenarios with noisy measurements and demonstrate that our method is able to generate a robust navigation strategy that is insensitive to imperfect sensing and works reliably in all situations. We also show that our method can be well generalized to scenarios that do not appear in our training data, including scenes with static obstacles and agents with different sizes. |
Persistent Identifier | http://hdl.handle.net/10722/308745 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Long, Pinxin | - |
dc.contributor.author | Liu, Wenxi | - |
dc.contributor.author | Pan, Jia | - |
dc.date.accessioned | 2021-12-08T07:50:02Z | - |
dc.date.available | 2021-12-08T07:50:02Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | IEEE Robotics and Automation Letters, 2017, v. 2, n. 2, p. 656-663 | - |
dc.identifier.uri | http://hdl.handle.net/10722/308745 | - |
dc.description.abstract | High-speed, low-latency obstacle avoidance that is insensitive to sensor noise is essential for enabling multiple decentralized robots to function reliably in cluttered and dynamic environments. While other distributed multiagent collision avoidance systems exist, these systems require online geometric optimization where tedious parameter tuning and perfect sensing are necessary. We present a novel end-to-end framework to generate reactive collision avoidance policy for efficient distributed multiagent navigation. Our method formulates an agent's navigation strategy as a deep neural network mapping from the observed noisy sensor measurements to the agent's steering commands in terms of movement velocity. We train the network on a large number of frames of collision avoidance data collected by repeatedly running a multiagent simulator with different parameter settings. We validate the learned deep neural network policy in a set of simulated and real scenarios with noisy measurements and demonstrate that our method is able to generate a robust navigation strategy that is insensitive to imperfect sensing and works reliably in all situations. We also show that our method can be well generalized to scenarios that do not appear in our training data, including scenes with static obstacles and agents with different sizes. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Robotics and Automation Letters | - |
dc.subject | Collision avoidance | - |
dc.subject | deep learning | - |
dc.subject | distributed robot systems | - |
dc.subject | multi-agent navigation | - |
dc.title | Deep-learned collision avoidance policy for distributed multiagent navigation | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/LRA.2017.2651371 | - |
dc.identifier.scopus | eid_2-s2.0-85042294932 | - |
dc.identifier.volume | 2 | - |
dc.identifier.issue | 2 | - |
dc.identifier.spage | 656 | - |
dc.identifier.epage | 663 | - |
dc.identifier.eissn | 2377-3766 | - |
dc.identifier.isi | WOS:000413736600037 | - |