Imitating driver behavior with generative adversarial networks

@article{Kuefler2017ImitatingDB,
  title={Imitating driver behavior with generative adversarial networks},
  author={Alex Kuefler and Jeremy Morton and Timothy A. Wheeler and Mykel J. Kochenderfer},
  journal={2017 IEEE Intelligent Vehicles Symposium (IV)},
  year={2017},
  pages={204-211}
}
The ability to accurately predict and simulate human driving behavior is critical for the development of intelligent transportation systems. Traditional modeling methods have employed simple parametric models and behavioral cloning. This paper adopts a method for overcoming the problem of cascading errors inherent in prior approaches, resulting in realistic behavior that is robust to trajectory perturbations. We extend Generative Adversarial Imitation Learning to the training of recurrent… Expand
A Probabilistic Framework for Imitating Human Race Driver Behavior
TLDR
Proabilistic Modeling of Driver behavior (ProMoD), a modular framework which splits the task of driver behavior modeling into multiple modules, and shows considerable advantages in imitation accuracy and robustness compared to other imitation learning algorithms. Expand
Modeling Car-Following Behaviors and Driving Styles with Generative Adversarial Imitation Learning
TLDR
The results show that the proposed model can reproduce drivers’ car-following trajectories and driving styles more accurately than the intelligent driver model and the recurrent neural network-based model, with the lowest average spacing error and speed validation error. Expand
Modeling Human Driving Behavior through Generative Adversarial Imitation Learning
TLDR
Experiments show that modifications to GAIL can successfully model highway driving behavior, accurately replicating human demonstrations and generating realistic, emergent behavior in the traffic flow arising from the interaction between driving agents. Expand
Multi-Agent Imitation Learning for Driving Simulation
TLDR
Compared with single-agent GAIL policies, policies generated by the PS-GAIL method prove superior at interacting stably in a multi-agent setting and capturing the emergent behavior of human drivers. Expand
Modeling Human Car-Following Behavior from Demonstration with Recurrent Neural Networks
The validity of simulation testing for autonomous vehicles depends on the ability to accurately simulate human driving behavior. This project seeks to train a model on an individual’s driving data,Expand
D-GAN : Autonomous Driving using Generative Adversarial Networks
We propose a framework for learning a policy directly from data in the contex of behavioral cloning. We explore environments in which a reward function R is not known. Classically, InverseExpand
Human-like Highway Trajectory Modeling based on Inverse Reinforcement Learning
TLDR
Experimental validations on lane-change prediction and human-like trajectory planning show that the proposed method approximates the state-of-the-art performance in modeling human trajectories, and is both interpretable and data-driven. Expand
Conditional Wasserstein Auto-Encoder for Interactive Vehicle Trajectory Prediction
TLDR
A conditional Wasserstein auto-encoder trajectory prediction model (TrajCWAE) that combines the representation learning and variational inference to generate predictions with multi-modal nature is proposed. Expand
Simultaneous policy learning and latent state inference for imitating driver behavior
TLDR
This work proposes a method for learning driver models that can account for unobserved states and shows that latent state driving policies outperform baseline methods at replicating driver behavior. Expand
ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
TLDR
The ChauffeurNet model can handle complex situations in simulation, and the perturbations then provide an important signal for these losses and lead to robustness of the learned model. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 45 REFERENCES
Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior
TLDR
This paper reveals that the strong performance of recurrent networks is due to the ability of the recurrent network to identify recent trends in the ego-vehicle's state, and recurrent networks are shown to perform as, well as feedforward networks with longer histories as inputs. Expand
High-speed highway scene prediction based on driver models learned from demonstrations
TLDR
This work shows how to use a realistic driver model learned from demonstrations via Inverse Reinforcement Learning to predict the long-term evolution of highway traffic scenes and demonstrates the capability of this approach to produce reliable, human-like scene predictions. Expand
Generative Adversarial Imitation Learning
TLDR
A new general framework for directly extracting a policy from data, as if it were obtained by reinforcement learning following inverse reinforcement learning, is proposed and a certain instantiation of this framework draws an analogy between imitation learning and generative adversarial networks. Expand
Analysis of microscopic behavior models for probabilistic modeling of driver behavior
TLDR
A comparative evaluation of several probabilistic microscopic human behavior models from the literature trained on naturalistic data for free-flow, car following, and lane change context-classes on highways shows that a new class of Bayesian network models outperforms the state of the art. Expand
Planning for Autonomous Cars that Leverage Effects on Human Actions
TLDR
The user study results suggest that the robot is indeed capable of eliciting desired changes in human state by planning using this dynamical system, in which the robot’s actions have immediate consequences on the state of the car, but also on human actions. Expand
Learning context sensitive behavior models from observations for predicting traffic situations
TLDR
An approach for learning continuous, non-linear, context dependent process models for the behavior of traffic participants from unlabeled observations that is naturally embedded into a Dynamic Bayesian Network that enables the prediction and estimation of traffic situations based on noisy and incomplete measurements. Expand
An Invitation to Imitation
TLDR
This work represents a summary from a very personal perspective of research on computationally effective methods for learning to imitate behavior to serve two audiences: to engage machine learning experts in the challenges of imitation learning and the interesting theoretical and practical distinctions with more familiar frameworks like statistical supervised learning theory. Expand
Estimation of Multivehicle Dynamics by Considering Contextual Information
TLDR
A probabilistic model to estimate the state of vehicles by considering interactions between drivers immersed in traffic is presented and validated using real-world data collected by a group of interacting ground vehicles. Expand
DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
TLDR
This paper proposes to map an input image to a small number of key perception indicators that directly relate to the affordance of a road/traffic state for driving and argues that the direct perception representation provides the right level of abstraction. Expand
Model-Free Imitation Learning with Policy Optimization
TLDR
Under the apprenticeship learning formalism, this work develops alternative model-free algorithms for finding a parameterized stochastic policy that performs at least as well as an expert policy on an unknown cost function, based on sample trajectories from the expert. Expand
...
1
2
3
4
5
...