scholarly journals Flow: Deep Reinforcement Learning for Control in SUMO

10.29007/dkzb ◽  
2018 ◽  
Author(s):  
Nishant Kheterpal ◽  
Kanaad Parvate ◽  
Cathy Wu ◽  
Aboudy Kreidieh ◽  
Eugene Vinitsky ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Computational Framework ◽  
Design Decisions ◽  
Learning Agents ◽  
Computational Overhead ◽  
Collision Handling ◽  
System Flow ◽  
Single Vehicle ◽  
Policy Optimization

We detail the motivation and design decisions underpinning Flow, a computational framework integrating SUMO with the deep reinforcement learning libraries rllab and RLlib, allowing researchers to apply deep reinforcement learning (RL) methods to traffic scenarios, and permitting vehicle and infrastructure control in highly varied traffic envi- ronments. Users of Flow can rapidly design a wide variety of traffic scenarios in SUMO, enabling the development of controllers for autonomous vehicles and intelligent infrastruc- ture across a broad range of settings.Flow facilitates the use of policy optimization algorithms to train controllers that can optimize for highly customizable traffic metrics, such as traffic flow or system-wide average velocity. Training reinforcement learning agents using such methods requires a massive amount of data, thus simulator reliability and scalability were major challenges in the development of Flow. A contribution of this work is a variety of practical techniques for overcoming such challenges with SUMO, including parallelizing policy rollouts, smart exception and collision handling, and leveraging subscriptions to reduce computational overhead.To demonstrate the resulting performance and reliability of Flow, we introduce the canonical single-lane ring road benchmark and briefly discuss prior work regarding that task. We then pose a more complex and challenging multi-lane setting and present a trained controller for a single vehicle that stabilizes the system. Flow is an open-source tool and available online at https://github.com/cathywu/flow.

scholarly journals An Efficiency Enhancing Methodology for Multiple Autonomous Vehicles in an Urban Network Adopting Deep Reinforcement Learning

2021 ◽  
Vol 11 (4) ◽  
pp. 1514 ◽  
Author(s):  
Quang-Duy Tran ◽  
Sang-Hoon Bae
Keyword(s):  
Reinforcement Learning ◽  
Traffic Congestion ◽  
Autonomous Vehicles ◽  
Penetration Rate ◽  
Autonomous Vehicle ◽  
Effective Means ◽  
Urban Network ◽  
Learning Agents ◽  
Policy Optimization ◽  
The Impact

To reduce the impact of congestion, it is necessary to improve our overall understanding of the influence of the autonomous vehicle. Recently, deep reinforcement learning has become an effective means of solving complex control tasks. Accordingly, we show an advanced deep reinforcement learning that investigates how the leading autonomous vehicles affect the urban network under a mixed-traffic environment. We also suggest a set of hyperparameters for achieving better performance. Firstly, we feed a set of hyperparameters into our deep reinforcement learning agents. Secondly, we investigate the leading autonomous vehicle experiment in the urban network with different autonomous vehicle penetration rates. Thirdly, the advantage of leading autonomous vehicles is evaluated using entire manual vehicle and leading manual vehicle experiments. Finally, the proximal policy optimization with a clipped objective is compared to the proximal policy optimization with an adaptive Kullback–Leibler penalty to verify the superiority of the proposed hyperparameter. We demonstrate that full automation traffic increased the average speed 1.27 times greater compared with the entire manual vehicle experiment. Our proposed method becomes significantly more effective at a higher autonomous vehicle penetration rate. Furthermore, the leading autonomous vehicles could help to mitigate traffic congestion.

scholarly journals Proximal Policy Optimization Through a Deep Reinforcement Learning Framework for Multiple Autonomous Vehicles at a Non-Signalized Intersection

2020 ◽  
Vol 10 (16) ◽  
pp. 5722 ◽  
Author(s):  
Duy Quang Tran ◽  
Sang-Hoon Bae
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Signalized Intersection ◽  
Continuous Control ◽  
Simulation Performance ◽  
Perceptron Algorithm ◽  
Learning Framework ◽  
Positive Effects ◽  
Policy Optimization

Advanced deep reinforcement learning shows promise as an approach to addressing continuous control tasks, especially in mixed-autonomy traffic. In this study, we present a deep reinforcement-learning-based model that considers the effectiveness of leading autonomous vehicles in mixed-autonomy traffic at a non-signalized intersection. This model integrates the Flow framework, the simulation of urban mobility simulator, and a reinforcement learning library. We also propose a set of proximal policy optimization hyperparameters to obtain reliable simulation performance. First, the leading autonomous vehicles at the non-signalized intersection are considered with varying autonomous vehicle penetration rates that range from 10% to 100% in 10% increments. Second, the proximal policy optimization hyperparameters are input into the multiple perceptron algorithm for the leading autonomous vehicle experiment. Finally, the superiority of the proposed model is evaluated using all human-driven vehicle and leading human-driven vehicle experiments. We demonstrate that full-autonomy traffic can improve the average speed and delay time by 1.38 times and 2.55 times, respectively, compared with all human-driven vehicle experiments. Our proposed method generates more positive effects when the autonomous vehicle penetration rate increases. Additionally, the leading autonomous vehicle experiment can be used to dissipate the stop-and-go waves at a non-signalized intersection.

Deep reinforcement learning based path tracking controller for autonomous vehicle

2020 ◽  
pp. 095440702095459
Author(s):  
I-Ming Chen ◽  
Ching-Yao Chan
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Path Tracking ◽  
Steering Control ◽  
Alternative Approach ◽  
Control Command ◽  
Pure Pursuit ◽  
Driving Condition ◽  
Policy Optimization

Path tracking is an essential task for autonomous vehicles (AV), for which controllers are designed to issue commands so that the AV will follow the planned path properly to ensure operational safety, comfort, and efficiency. While solving the time-varying nonlinear vehicle dynamic problem is still challenging today, deep neural network (NN) methods, with their capability to deal with nonlinear systems, provide an alternative approach to tackle the difficulties. This study explores the potential of using deep reinforcement learning (DRL) for vehicle control and applies it to the path tracking task. In this study, proximal policy optimization (PPO) is selected as the DRL algorithm and is combined with the conventional pure pursuit (PP) method to structure the vehicle controller architecture. The PP method is used to generate a baseline steering control command, and the PPO is used to derive a correction command to mitigate the inaccuracy associated with the baseline from PP. The blend of the two controllers makes the overall operation more robust and adaptive and attains the optimality to improve tracking performance. In this paper, the structure, settings and training process of the PPO are described. Simulation experiments are carried out based on the proposed methodology, and the results show that the path tracking capability in a low-speed driving condition is significantly enhanced.

scholarly journals Design of a Reinforcement Learning-Based Lane Keeping Planning Agent for Automated Vehicles

2020 ◽  
Vol 10 (20) ◽  
pp. 7171
Author(s):  
Bálint Kővári ◽  
Ferenc Hegedüs ◽  
Tamás Bécsi
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Autonomous Vehicles ◽  
High Performance ◽  
Search Algorithm ◽  
Tree Search ◽  
Monte Carlo Tree Search ◽  
Learning Agents ◽  
Combined Solution ◽  
Lane Keeping

Reinforcement learning-based approaches are widely studied in the literature for solving different control tasks for Connected and Autonomous Vehicles, from which this paper deals with the problem of lateral control of a dynamic nonlinear vehicle model, performing the task of lane-keeping. In this area, the appropriate formulation of the goals and environment information is crucial, for which the research outlines the importance of lookahead information, enabling to accomplish maneuvers with complex trajectories. Another critical part is the real-time manner of the problem. On the one hand, optimization or search based methods, such as the presented Monte Carlo Tree Search method, can solve the problem with the trade-off of high numerical complexity. On the other hand, single Reinforcement Learning agents struggle to learn these tasks with high performance, though they have the advantage that after the training process, they can operate in a real-time manner. Two planning agent structures are proposed in the paper to resolve this duality, where the machine learning agents aid the tree search algorithm. As a result, the combined solution provides high performance and low computational needs.

scholarly journals An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users

Biomimetics ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 13
Author(s):  
Adam Bignold ◽  
Francisco Cruz ◽  
Richard Dazeley ◽  
Peter Vamplew ◽  
Cameron Foale
Keyword(s):  
Reinforcement Learning ◽  
Information Source ◽  
Human Interaction ◽  
Evaluation Methodology ◽  
External Information ◽  
Preliminary Evaluation ◽  
Learning Agents ◽  
Learning Agent ◽  
Knowledge Bias ◽  
The Impact

Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating reinforcement learning algorithms, it is common to repeat experiments as parameters are altered or to gain a sufficient sample size. In this regard, to require human interaction every time an experiment is restarted is undesirable, particularly when the expense in doing so can be considerable. Additionally, reusing the same people for the experiment introduces bias, as they will learn the behaviour of the agent and the dynamics of the environment. This paper presents a methodology for evaluating interactive reinforcement learning agents by employing simulated users. Simulated users allow human knowledge, bias, and interaction to be simulated. The use of simulated users allows the development and testing of reinforcement learning agents, and can provide indicative results of agent performance under defined human constraints. While simulated users are no replacement for actual humans, they do offer an affordable and fast alternative for evaluative assisted agents. We introduce a method for performing a preliminary evaluation utilising simulated users to show how performance changes depending on the type of user assisting the agent. Moreover, we describe how human interaction may be simulated, and present an experiment illustrating the applicability of simulating users in evaluating agent performance when assisted by different types of trainers. Experimental results show that the use of this methodology allows for greater insight into the performance of interactive reinforcement learning agents when advised by different users. The use of simulated users with varying characteristics allows for evaluation of the impact of those characteristics on the behaviour of the learning agent.

scholarly journals Air Learning: a deep reinforcement learning gym for autonomous aerial robot visual navigation

2021 ◽  
Author(s):  
Srivatsan Krishnan ◽  
Behzad Boroujerdian ◽  
William Fu ◽  
Aleksandra Faust ◽  
Vijay Janapa Reddi
Keyword(s):  
Reinforcement Learning ◽  
Embedded System ◽  
Broad Class ◽  
Visual Navigation ◽  
Raspberry Pi ◽  
Latency Distribution ◽  
Hardware In The Loop ◽  
Resource Constrained ◽  
Aerial Robot ◽  
Policy Optimization

AbstractWe introduce Air Learning, an open-source simulator, and a gym environment for deep reinforcement learning research on resource-constrained aerial robots. Equipped with domain randomization, Air Learning exposes a UAV agent to a diverse set of challenging scenarios. We seed the toolset with point-to-point obstacle avoidance tasks in three different environments and Deep Q Networks (DQN) and Proximal Policy Optimization (PPO) trainers. Air Learning assesses the policies’ performance under various quality-of-flight (QoF) metrics, such as the energy consumed, endurance, and the average trajectory length, on resource-constrained embedded platforms like a Raspberry Pi. We find that the trajectories on an embedded Ras-Pi are vastly different from those predicted on a high-end desktop system, resulting in up to $$40\%$$ 40 % longer trajectories in one of the environments. To understand the source of such discrepancies, we use Air Learning to artificially degrade high-end desktop performance to mimic what happens on a low-end embedded system. We then propose a mitigation technique that uses the hardware-in-the-loop to determine the latency distribution of running the policy on the target platform (onboard compute on aerial robot). A randomly sampled latency from the latency distribution is then added as an artificial delay within the training loop. Training the policy with artificial delays allows us to minimize the hardware gap (discrepancy in the flight time metric reduced from 37.73% to 0.5%). Thus, Air Learning with hardware-in-the-loop characterizes those differences and exposes how the onboard compute’s choice affects the aerial robot’s performance. We also conduct reliability studies to assess the effect of sensor failures on the learned policies. All put together, Air Learning enables a broad class of deep RL research on UAVs. The source code is available at: https://github.com/harvard-edge/AirLearning.

Modeling human-like longitudinal driver model for intelligent vehicles based on reinforcement learning

2021 ◽  
pp. 095440702098357
Author(s):  
Ju Xie ◽  
Xing Xu ◽  
Feng Wang ◽  
Haobin Jiang
Keyword(s):  
Reinforcement Learning ◽  
Comprehensive Evaluation ◽  
Path Following ◽  
Intelligent Vehicles ◽  
Driver Model ◽  
Control Center ◽  
Training Performance ◽  
Learning Agents ◽  
System A ◽  
And Control

The driver model is the decision-making and control center of intelligent vehicle. In order to improve the adaptability of intelligent vehicles under complex driving conditions, and simulate the manipulation characteristics of the skilled driver under the driver-vehicle-road closed-loop system, a kind of human-like longitudinal driver model for intelligent vehicles based on reinforcement learning is proposed. This paper builds the lateral driver model for intelligent vehicles based on optimal preview control theory. Then, the control correction link of longitudinal driver model is established to calculate the throttle opening or brake pedal travel for the desired longitudinal acceleration. Moreover, the reinforcement learning agents for longitudinal driver model is parallel trained by comprehensive evaluation index and skilled driver data. Lastly, training performance and scenarios verification between the simulation experiment and the real car test are performed to verify the effectiveness of the reinforcement learning based longitudinal driver model. The results show that the proposed human-like longitudinal driver model based on reinforcement learning can help intelligent vehicles effectively imitate the speed control behavior of the skilled driver in various path-following scenarios.

Sign in / Sign up

Export Citation Format

Share Document