Enabling Mixed Autonomy Traffic Control

We demonstrate a new capability of automated vehicles: mixed autonomy traffic control. With this new capability, automated vehicles can shape the traffic flows composed of other non-automated vehicles, which has the promise to improve safety, efficiency, and energy outcomes in transportation systems at a societal scale. Investigating mixed autonomy mobile traffic control must be done in situ given that the complex dynamics of other drivers and their response to a team of automated vehicles cannot be effectively modeled. This capability has been blocked because there is no existing scalable and affordable platform for experimental control. This paper introduces an extensible open-source hardware and software platform, enabling a team of 100 vehicles to execute several different vehicular control algorithms as a collaborative fleet, composed of three different makes and models, which drove 22752 miles in a combined 1022 hours, over 5 days in Nashville, TN in November 2022.

So you think you can track?

This work introduces a multi-camera tracking dataset consisting of 234 hours of video data recorded concurrently from 234 overlapping HD cameras covering a 4.2 mile stretch of 8-10 lane interstate highway near Nashville, TN. The video is recorded during a period of high traffic density with 500+ objects typically visible within the scene and typical object longevities of 3-15 minutes. GPS trajectories from 270 vehicle passes through the scene are manually corrected in the video data to provide a set of ground-truth trajectories for recall-oriented tracking metrics, and object detections are provided for each camera in the scene (159 million total before cross-camera fusion). Initial benchmarking of tracking-by-detection algorithms is performed against the GPS trajectories, and a best HOTA of only 9.5% is obtained (best recall 75.9% at IOU 0.1, 47.9 average IDs per ground truth object), indicating the benchmarked trackers do not perform sufficiently well at the long temporal and spatial durations required for traffic scene understanding.

Decentralized Vehicle Coordination: The Berkeley DeepDrive Drone Dataset

Decentralized multiagent planning has been an important field of research in robotics. An interesting and impactful application in the field is decentralized vehicle coordination in understructured road environments. For example, in an intersection, it is useful yet difficult to deconflict multiple vehicles of intersecting paths in absence of a central coordinator. We learn from common sense that, for a vehicle to navigate through such understructured environments, the driver must understand and conform to the implicit "social etiquette" observed by nearby drivers. To study this implicit driving protocol, we collect the Berkeley DeepDrive Drone dataset. The dataset contains 1) a set of aerial videos recording understructured driving, 2) a collection of images and annotations to train vehicle detection models, and 3) a kit of development scripts for illustrating typical usages. We believe that the dataset is of primary interest for studying decentralized multiagent planning employed by human drivers and, of secondary interest, for computer vision in remote sensing settings.

Multi-Adversarial Safety Analysis for Autonomous Vehicles

This work in progress considers reachability-based safety analysis in the domain of autonomous driving in multi-agent systems. We formulate the safety problem for a car following scenario as a differential game and study how different modelling strategies yield very different behaviors regardless of the validity of the strategies in other scenarios. Given the nature of real-life driving scenarios, we propose a modeling strategy in our formulation that accounts for subtle interactions between agents, and compare its Hamiltonian results to other baselines. Our formulation encourages reduction of conservativeness in Hamilton-Jacobi safety analysis to provide better safety guarantees during navigation.

The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games

Proximal Policy Optimization (PPO) is a popular on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent problems. In this work, we investigate Multi-Agent PPO (MAPPO), a multi-agent PPO variant which adopts a centralized value function. Using a 1-GPU desktop, we show that MAPPO achieves performance comparable to the state-of-the-art in three popular multi-agent testbeds: the Particle World environments, Starcraft II Micromanagement Tasks, and the Hanabi Challenge, with minimal hyperparameter tuning and without any domain-specific algorithmic modifications or architectures. In the majority of environments, we find that compared to off-policy baselines, MAPPO achieves better or comparable sample complexity as well as substantially faster running time. Finally, we present 5 factors most influential to MAPPO's practical performance with ablation studies.

A Graph Convolutional Network with Signal Phasing Information for Arterial Traffic Prediction

Accurate and reliable prediction of traffic measurements plays a crucial role in the development of modern intelligent transportation systems. Due to more complex road geometries and the presence of signal control, arterial traffic prediction is a level above freeway traffic prediction. Many existing studies on arterial traffic prediction only consider temporal measurements of flow and occupancy from loop sensors and neglect the rich spatial relationships between upstream and downstream detectors. As a result, they often suffer large prediction errors, especially for long horizons. We fill this gap by enhancing a deep learning approach, Diffusion Convolutional Recurrent Neural Network, with spatial information generated from signal timing plans at targeted intersections. Traffic at signalized intersections is modeled as a diffusion process with a transition matrix constructed from the phase splits of the signal phase timing plan. We apply this novel method to predict traffic flow from loop sensor measurements and signal timing plans at an arterial intersection in Arcadia, CA. We demonstrate that our proposed method yields superior forecasts; for a prediction horizon of 30 minutes, we cut the MAPE down to 16% for morning peaks, 10% for off peaks, and even 8% for afternoon peaks. In addition, we exemplify the robustness of our model through a number of experiments with various settings in detector coverage, detector type, and data quality.

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

A wide range of reinforcement learning (RL) problems - including robustness, transfer learning, unsupervised RL, and emergent complexity - require specifying a distribution of tasks or environments in which a policy will be trained. However, creating a useful distribution of environments is error prone, and takes a significant amount of developer time and effort. We propose Unsupervised Environment Design (UED) as an alternative paradigm, where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid, solvable environments. Existing approaches to automatically generating environments suffer from common failure modes: domain randomization cannot generate structure or adapt the difficulty of the environment to the agent's learning progress, and minimax adversarial training leads to worst-case environments that are often unsolvable. To generate structured, solvable environments for our protagonist agent, we introduce a second, antagonist agent that is allied with the environment-generating adversary. The adversary is motivated to generate environments which maximize regret, defined as the difference between the protagonist and antagonist agent's return. We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED). Our experiments demonstrate that PAIRED produces a natural curriculum of increasingly complex environments, and PAIRED agents achieve higher zero-shot transfer performance when tested in highly novel environments.

Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL

We study the ability of autonomous vehicles to improve the throughput of a bottleneck using a fully decentralized control scheme in a mixed autonomy setting. We consider the problem of improving the throughput of a scaled model of the San Francisco-Oakland Bay Bridge: a two-stage bottleneck where four lanes reduce to two and then reduce to one. Although there is extensive work examining variants of bottleneck control in a centralized setting, there is less study of the challenging multi-agent setting where the large number of interacting AVs leads to significant optimization difficulties for reinforcement learning methods. We apply multi-agent reinforcement algorithms to this problem and demonstrate that significant improvements in bottleneck throughput, from 20\% at a 5\% penetration rate to 33\% at a 40\% penetration rate, can be achieved. We compare our results to a hand-designed feedback controller and demonstrate that our results sharply outperform the feedback controller despite extensive tuning. Additionally, we demonstrate that the RL-based controllers adopt a robust strategy that works across penetration rates whereas the feedback controllers degrade immediately upon penetration rate variation. We investigate the feasibility of both action and observation decentralization and demonstrate that effective strategies are possible using purely local sensing. Finally, we open-source our code at https://github.com/eugenevinitsky/decentralized_bottlenecks.

Robust Reinforcement Learning using Adversarial Populations

Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness, failing catastrophically when the underlying system dynamics are perturbed. The Robust RL formulation tackles this by adding worst-case adversarial noise to the dynamics and constructing the noise distribution as the solution to a zero-sum minimax game. However, existing work on learning solutions to the Robust RL formulation has primarily focused on training a single RL agent against a single adversary. In this work, we demonstrate that using a single adversary does not consistently yield robustness to dynamics variations under standard parametrizations of the adversary; the resulting policy is highly exploitable by new adversaries. We propose a population-based augmentation to the Robust RL formulation in which we randomly initialize a population of adversaries and sample from the population uniformly during training. We empirically validate across robotics benchmarks that the use of an adversarial population results in a more robust policy that also improves out-of-distribution generalization. Finally, we demonstrate that this approach provides comparable robustness and generalization as domain randomization on these benchmarks while avoiding a ubiquitous domain randomization failure mode.

Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehicles

Using deep reinforcement learning, we train control policies for autonomous vehicles leading a platoon of vehicles onto a roundabout. Using Flow, a library for deep reinforcement learning in micro-simulators, we train two policies, one policy with noise injected into the state and action space and one without any injected noise. In simulation, the autonomous vehicle learns an emergent metering behavior for both policies in which it slows to allow for smoother merging. We then directly transfer this policy without any tuning to the University of Delaware Scaled Smart City (UDSSC), a 1:25 scale testbed for connected and automated vehicles. We characterize the performance of both policies on the scaled city. We show that the noise-free policy winds up crashing and only occasionally metering. However, the noise-injected policy consistently performs the metering behavior and remains collision-free, suggesting that the noise helps with the zero-shot policy transfer. Additionally, the transferred, noise-injected policy leads to a 5% reduction of average travel time and a reduction of 22% in maximum travel time in the UDSSC. Videos of the controllers can be found at https://sites.google.com/view/iccps-policy-transfer.