Deep-Learned Collision Avoidance Policy for Distributed Multiagent Navigation

By Pinxin Long, Wenxi Liu, Jia Pan. 2016

191 citations recorded by the source corpus.

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. Videos are available at https://sites.google.com/view/deepmaca.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tingxiang Fan
2. Jia Pan
3. Wenxi Liu
4. Pinxin Long
5. Lei Tai
6. Michael Everett
7. Jonathan P. How
8. Yu Fan Chen

In Computer Vision and Pattern Recognition

1. Tingxiang Fan
2. Lei Tai
3. Pinxin Long
4. Jia Pan
5. Wenxi Liu
6. H. Zhang
7. Michael Everett
8. Yu Fan Chen

In Control and Systems Engineering

1. Tingxiang Fan
2. Lei Tai
3. Wenxi Liu
4. Jia Pan
5. Pinxin Long
6. Michael Everett
7. Quan Pan
8. Yu Fan Chen

Citations in the corpus

• Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning (2017, methodology): “Sensor-level collision avoidance policies are often modeled by deep neural networks (DNNs) [10], [11] and trained using supervised learning on a large dataset.”
• Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Method (2018, methodology): “The most similar works related to our topic is proposed in [13] and [8].”
• Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning (2018, background): “(a) GA3C-CADRL trajectories with n ∈ [2, 3, 4] agents”
• Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, background): “Additional to single-robot tasks, Long et al. (2016) proposed a multi-agent collision avoidance policy by DNN through the observations about the conditions of other moving agents.”
• Crowd-Robot Interaction: Crowd-Aware Robot Navigation With Attention-Based Deep Reinforcement Learning (2018, result): “As pointed out in [32], tuning ORCA towards an objective function can be a tedious and challenging process compared with learning-based methods.”
• Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios (2020, methodology): “This article is an extension of our previous conference version (Long et al., 2017a), which presents a multi-robot navigation policy that demonstrates the state-of-the-art performance in simulated scenarios.”