MADRaS : Multi Agent Driving Simulator

Santara, Anirban; Rudra, Sohan; Buridi, Sree Aditya; Kaushik, Meha; Naik, Abhishek; Kaul, Bharat; Ravindran, Balaraman

doi:10.1613/jair.1.12531

Cited by 16 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reward functions for lane following may be based on throttle [28], speed [38], speed parallel to lane [39][40] [41][42] [29], traveled distance [43], and progress [38], and can include penalties for leaving the lane [28], distance from lane center [42][40] [41], or collision [43] [41].…”

Section: Reward Functionmentioning

confidence: 99%

Enhancing Visual Domain Randomization with Real Images for Sim-to-Real Transfer

Béres¹,

Gyires-Tóth²

2023

Infocommunications journal

View full text Add to dashboard Cite

In order to train reinforcement learning algorithms, a significant amount of experience is required, so it is common practice to train them in simulation, even when they are intended to be applied in the real world. To improve robustness, camerabased agents can be trained using visual domain randomization, which involves changing the visual characteristics of the simulator between training episodes in order to improve their resilience to visual changes in their environment. In this work, we propose a method, which includes realworld images alongside visual domain randomization in the reinforcement learning training procedure to further enhance the performance after sim-to-real transfer. We train variational autoencoders using both real and simulated frames, and the representations produced by the encoders are then used to train reinforcement learning agents. The proposed method is evaluated against a variety of baselines, including direct and indirect visual domain randomization, end-to-end reinforcement learning, and supervised and unsupervised state representation learning. By controlling a differential drive vehicle using only camera images, the method is tested in the Duckietown self-driving car environment. We demonstrate through our experimental results that our method improves learnt representation effectiveness and robustness by achieving the best performance of all tested methods.

show abstract

Section: Reward Functionmentioning

confidence: 99%

Enhancing Visual Domain Randomization with Real Images for Sim-to-Real Transfer

Béres¹,

Gyires-Tóth²

2023

Infocommunications journal

View full text Add to dashboard Cite

show abstract

“…Google Research Football [17] provides a few zero-sum multi-agent environments featuring two teams consisting of several agents. 3D SUMMIT [6] 3D MACAD [24] 3D Highway-env [19] 2D Sim4CV [21] 3D Duckietown [26] 3D SMARTS [38] 2D MADRaS [31] 2D DriverGym [16] 2D DeepDrive-Zero [28] 2D MetaDrive [20] 3D VISTA [20] 3D Nocturne 2D…”

Section: Partially Observed Multi-agent Benchmarksmentioning

confidence: 99%

Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world

Vinitsky¹,

Lichtle²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

We introduce Nocturne, a new 2D driving simulator for investigating multi-agent coordination under partial observability. The focus of Nocturne is to enable research into inference and theory of mind in real-world multi-agent settings without the computational overhead of computer vision and feature extraction from images. Agents in this simulator only observe an obstructed view of the scene, mimicking human visual sensing constraints. Unlike existing benchmarks that are bottlenecked by rendering human-like observations directly using a camera input, Nocturne uses efficient intersection methods to compute a vectorized set of visible features in a C++ back-end, allowing the simulator to run at 2000+ steps-per-second. Using open-source trajectory and map data, we construct a simulator to load and replay arbitrary trajectories and scenes from real-world driving data. Using this environment, we benchmark reinforcement-learning and imitation-learning agents and demonstrate that the agents are quite far from human-level coordination ability and deviate significantly from the expert trajectories.

show abstract

“…The Multi-Agent Driving Simulator (MADRAS) is a multi-agent driving simulator for training autonomous cars with motion planning. 11 MADRAS is built on top of TORCS and adds multi-agent training, inter-car communications, noisy observations, and stochastic actions.…”

Section: Select Outdoor Simulatorsmentioning

confidence: 99%

ARORA & NavSim: a simulator system for training autonomous agents with geospecific data

Fandango¹,

Gutierrez²,

Hoayun³

et al. 2022

Artificial Intelligence and Machine Learning in Defense Applications IV

View full text Add to dashboard Cite

This study accompanies the initial public release of the software for ARORA, or A Realistic Open environment for Rapid Agent training, and marks a high point of several years of work for the mature and completely open ARORA simulator. The purpose of ARORA is to support the training of an autonomous agent for tasks associated with a large-scale and geospecific outdoor urban environment, including the task of navigation as a car. The study elaborates on the simulator's architecture, agent, and environment. For the environment, ARORA provides an improvement on similar simulators through an unconstrained geospecific environment with detailed semantic annotation. The agent is represented as a car available with four different options of physics fidelity. The agent also has sensors available: a pose sensor, a camera sensor, and a set of three proximity sensors. Future use cases from training extend to both civilians and militaries (including human training and wargaming), in terms of training autonomous agents in outdoor urban environments. The study also presents a brief description of NavSim, a Python-based companion tool. The purpose of NavSim is to connect to ARORA (or any other similar simulator) and train an agent using reinforcement-learning algorithms. The study also provides challenges in development and subsequent work-arounds and solutions. The goal of the ARORA & NavSim system is to provide communities with a high-fidelity, publicly available, free, and open-source system for training an autonomous agent as a car.

show abstract

MADRaS : Multi Agent Driving Simulator

Cited by 16 publications

References 36 publications

Enhancing Visual Domain Randomization with Real Images for Sim-to-Real Transfer

Enhancing Visual Domain Randomization with Real Images for Sim-to-Real Transfer

Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world

ARORA & NavSim: a simulator system for training autonomous agents with geospecific data

Contact Info

Product

Resources

About