Corpus ID: 208309914

Social Attention for Autonomous Decision-Making in Dense Traffic

@article{Leurent2019SocialAF,
  title={Social Attention for Autonomous Decision-Making in Dense Traffic},
  author={Edouard Leurent and Jean Pierre Mercat},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.12250}
}
We study the design of learning architectures for behavioural planning in a dense traffic setting. Such architectures should deal with a varying number of nearby vehicles , be invariant to the ordering chosen to describe them, while staying accurate and compact. We observe that the two most popular representations in the literature do not fit these criteria, and perform badly on an complex negotiation task. We propose an attention-based architecture that satisfies all these properties and… Expand
Spatial Attention for Autonomous Decision-making in Highway Scene
  • Shuwei Zhang, Yutian Wu, H. Ogai
  • Computer Science
  • 2020 59th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE)
  • 2020
TLDR
This work introduces a spatial attention module to calculate weights for each vehicle and integrate the attention mechanism into Deep Q network to make decision actions, and shows the proposed method can get significant performance gains compared with other deep reinforcement learning methods by using two kinds of metrics. Expand
Vision Transformer for Learning Driving Policies in Complex Multi-Agent Environments
TLDR
This work proposes to use Vision Transformer to learn a driving policy in urban settings with birds-eye-view (BEV) input images and demonstrates that a DQN agent with a ViT backbone outperforms baseline algorithms with ConvNet backbones pre-trained in various ways. Expand
A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios
TLDR
A benchmark for training and testing RL-based autonomous driving agents in complex intersection scenarios, which is called RL-CIS is proposed, and a set of baselines are deployed consists of various algorithms. Expand
StylePredict: Machine Theory of Mind for Human Driver Behavior From Trajectories
Studies have shown that autonomous vehicles (AVs) behave conservatively in a traffic environment composed of human drivers and do not adapt to local conditions and socio-cultural norms. It is knownExpand
Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning
TLDR
This paper proposes a training, testing, and evaluation pipeline for the lane-changing task from the perspective of deep reinforcement learning, and trains several state-of-the-artDeep reinforcement learning methods in the designed training scenarios and provides the benchmark metrics evaluation results of the trained models in the test scenarios. Expand
Decision-making at Unsignalized Intersection for Autonomous Vehicles: Left-turn Maneuver with Deep Reinforcement Learning
TLDR
Simulation results indicate that the presented decision-making strategy could efficaciously reduce the collision rate and improve transport efficiency, and also reveals that the constructed left-turn control structure has a great potential to be applied in real-time. Expand
Addressing Action Oscillations through Learning Policy Inertia
TLDR
Policy Inertia Controller is introduced which serves as a generic plug-in framework to off-the-shelf DRL algorithms, to enables adaptive trade-off between the optimality and smoothness of the learned policy in a formal way and a practical DRL algorithm, namely Nested Soft Actor-Critic is derived. Expand
Policy learning with partial observation and mechanical constraints for multi-person modeling
TLDR
This work proposes sequential generative models with partial observation and mechanical constraints, which can visualize whose information the agents utilize and can generate biologically plausible actions. Expand
MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation
  • Xiaoyi Chen, P. Chaudhari
  • Computer Science, Mathematics
  • 2021 IEEE International Conference on Robotics and Automation (ICRA)
  • 2021
TLDR
MIDAS uses an attention mechanism to handle an arbitrary number of other agents and includes a "driver-type" parameter to learn a single policy that works across different planning objectives and is safer and more efficient than existing approaches to interaction-aware decision-making. Expand
DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks
TLDR
DQ-GAT is proposed to achieve scalable and proactive autonomous driving, where graph attention-based networks are used to implicitly model interactions, and asynchronous deep Q-learning is employed to train the network end-to-end in an unsupervised manner. Expand
...
1
2
...

References

SHOWING 1-10 OF 40 REFERENCES
Social Attention: Modeling Attention in Human Crowds
TLDR
This work proposes Social Attention, a novel trajectory prediction model that captures the relative importance of each person when navigating in the crowd, irrespective of their proximity, and demonstrates the performance against a state-of-the-art approach on two publicly available crowd datasets. Expand
PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
TLDR
A probabilistic forecasting model of future interactions between a variable number of agents that performs both standard forecasting and the novel task of conditional forecasting, which reasons about how all agents will likely respond to the goal of a controlled agent. Expand
Socially aware motion planning with deep reinforcement learning
TLDR
Using deep reinforcement learning, this work develops a time-efficient navigation policy that respects common social norms and is shown to enable fully autonomous navigation of a robotic vehicle moving at human walking speed in an environment with many pedestrians. Expand
Non-local Social Pooling for Vehicle Trajectory Prediction
TLDR
The proposed approach to predict the motion of vehicles surrounding a target vehicle in a highway environment is compared with the state-of-the-art using two naturalistic driving datasets: Next Generation Simulation (NGSIM) and the new highD Dataset. Expand
Pedestrian Prediction by Planning Using Deep Neural Networks
TLDR
This work proposes to predict pedestrians using goal-directed planning using a mixture density function for possible destinations and shows that this entire system can be modeled as one monolithic neural network and trained via inverse reinforcement learning. Expand
CAR-Net: Clairvoyant Attentive Recurrent Network
TLDR
A Clairvoyant Attentive Recurrent Network (CAR-Net) that learns where to look in a large image of the scene when solving the path prediction task, and shows CAR-Net’s ability to generalize to unseen scenes. Expand
DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation
TLDR
This paper investigates the crowd-sourcedhyperparameter tuning of the policy network that resulted from the first iteration of the DeepTraffic competition where thousands of participants actively searched through the hyperparameter space. Expand
SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints
TLDR
SoPhie is presented; an interpretable framework based on Generative Adversarial Network (GAN), which leverages two sources of information, the path history of all the agents in a scene, and the scene context information, using images of the scene. Expand
Tactical Decision Making for Lane Changing with Deep Reinforcement Learning
TLDR
This paper presents a framework that demonstrates a more structured and data efficient alternative to end-to-end complete policy learning on problems where the high-level policy is hard to formulate using traditional optimization or rule based methods but well designed low-level controllers are available. Expand
Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making
TLDR
This paper proposes several practical components that can speed up deep reinforcement learning algorithms towards tactical decision making tasks: non-uniform action skipping as a more stable alternative to action-repetition frame skipping, a counter-based penalty for lanes on which ego vehicle has less right-of-road, and heuristic inference-time action masking for apparently undesirable actions. Expand
...
1
2
3
4
...