The AI Driving Olympics at NeurIPS 2018

Zilly, Julian; Tani, Jacopo; Considine, Breandan; Mehta, Bhairav; Daniele, Andrea F.; Diaz, Manfred; Bernasconi, Gianmarco; Ruch, Claudio; Hakenberg, Jan; Golemo, Florian; Bowser, A. Kirsten; Walter, Matthew R.; Hristov, Ruslan; Mallya, Sunil; Censi, Andrea; Paull, Liam

doi:10.48550/arxiv.1903.02503

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the control commands have an unsteady delay in the real world consisting of the network delay and inference time, which results in the need for more corrections accomplished by generating turning commands. 4) Comparing with state-of-the-art results: The AI Driving Olympics (AI-DO) is a series of competitions focusing on AI for self-driving vehicles in the Duckietown environment [27]. The competition had three rounds in 2018 and 2019 organized at the NeurIPS and ICRA conferences.…”

Section: Resultsmentioning

confidence: 99%

Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World

Almási,

Moni,

Gyires-Tóth

2020

Preprint

View full text Add to dashboard Cite

Deep Reinforcement Learning (DRL) has been successfully used to solve different challenges, e.g. complex board and computer games, recently. However, solving real-world robotics tasks with DRL seems to be a more difficult challenge. The desired approach would be to train the agent in a simulator and transfer it to the real world. Still, models trained in a simulator tend to perform poorly in real-world environments due to the differences. In this paper, we present a DRL-based algorithm that is capable of performing autonomous robot control using Deep Q-Networks (DQN). In our approach, the agent is trained in a simulated environment and it is able to navigate both in a simulated and real-world environment. The method is evaluated in the Duckietown environment, where the agent has to follow the lane based on a monocular camera input. The trained agent is able to run on limited hardware resources and its performance is comparable to state-of-the-art approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World

Almási,

Moni,

Gyires-Tóth

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…We trained a neural network-based controller that takes images from a forward-looking monocular camera and produces control signals to drive a vehicle in the right lane of a twoway road. The vehicle to be controlled is a small differentialwheeled mobile robot, a so-called Duckiebot, which is part of the Duckietown ecosystem [7], a simple and accessible platform for research and education on mobile robotics and autonomous vehicles. The primary objective is to travel as far as possible under a given time, without leaving the road (while lane departure is allowed, but not preferred).…”

Section: Methodsmentioning

confidence: 99%

Sim-to-real reinforcement learning applied to end-to-end vehicle control

Kalapos

Gór²,

Moni³

et al. 2020

2020 23rd International Symposium on Measurement and Control in Robotics (ISMCR)

View full text Add to dashboard Cite

In this work, we study vision-based end-to-end reinforcement learning on vehicle control problems, such as lane following and collision avoidance. Our controller policy is able to control a small-scale robot to follow the right-hand lane of a real two-lane road, while its training was solely carried out in a simulation. Our model, realized by a simple, convolutional network, only relies on images of a forward-facing monocular camera and generates continuous actions that directly control the vehicle. To train this policy we used Proximal Policy Optimization, and to achieve the generalization capability required for real performance we used domain randomization. We carried out thorough analysis of the trained policy, by measuring multiple performance metrics and comparing these to baselines that rely on other methods. To assess the quality of the simulation-toreality transfer learning process and the performance of the controller in the real world, we measured simple metrics on a real track and compared these with results from a matching simulation. Further analysis was carried out by visualizing salient object maps.

show abstract

“…We collected 10 agent submissions from a lane-following challenge from the AI Driving Olympics (AIDO) [44]. Each submission consist of a controller that is designed to drive a Duckiebot along a lane, following the center as closely as possible.…”

Section: A Duckietown Simulator Predictivitymentioning

confidence: 99%

On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents

Courchesne¹,

Censi²,

Paull³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

In many situations it is either impossible or impractical to develop and evaluate agents entirely on the target domain on which they will be deployed. This is particularly true in robotics, where doing experiments on hardware is much more arduous than in simulation. This has become arguably more so in the case of learning-based agents. To this end, considerable recent effort has been devoted to developing increasingly realistic and higher fidelity simulators. However, we lack any principled way to evaluate how good a "proxy domain" is, specifically in terms of how useful it is in helping us achieve our end objective of building an agent that performs well in the target domain. In this work, we investigate methods to address this need. We begin by clearly separating two uses of proxy domains that are often conflated: 1) their ability to be a faithful predictor of agent performance and 2) their ability to be a useful tool for learning. In this paper, we attempt to clarify the role of proxy domains and establish new proxy usefulness (PU) metrics to compare the usefulness of different proxy domains. We propose the relative predictive PU to assess the predictive ability of a proxy domain and the learning PU to quantify the usefulness of a proxy as a tool to generate learning data. Furthermore, we argue that the value of a proxy is conditioned on the task that it is being used to help solve. We demonstrate how these new metrics can be used to optimize parameters of the proxy domain for which obtaining ground truth via system identification is not trivial.

show abstract

The AI Driving Olympics at NeurIPS 2018

Cited by 3 publications

References 0 publications

Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World

Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World

Sim-to-real reinforcement learning applied to end-to-end vehicle control

On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents

Contact Info

Product

Resources

About