Autonomous car racing is a major challenge in robotics. It raises fundamental problems for classical approaches such as planning minimum-time trajectories under uncertain dynamics and controlling the car at the limits of its handling. Besides, the requirement of minimizing the lap time, which is a sparse objective, and the difficulty of collecting training data from human experts have also hindered researchers from directly applying learning-based approaches to solve the problem. In the present work, we propose a learning-based system for autonomous car racing by leveraging a high-fidelity physical car simulation, a course-progress proxy reward, and deep reinforcement learning. We deploy our system in Gran Turismo Sport, a world-leading car simulator known for its realistic physics simulation of different race cars and tracks, which is even used to recruit human race car drivers. Our trained policy achieves autonomous racing performance that goes beyond what had been achieved so far by the built-in AI, and at the same time, outperforms the fastest driver in a dataset of over 50,000 human players.
<p>Detecting seismic signals and identifying their origin is more and more used for understanding environmental activity. This usually depends on a good signal/noise ratio (S/N), especially for the more distant sources.</p><p>A test area for detection and identification is the urban setting of the University of Vienna, a challenging environment with more than 4000 strong-acceleration events per day. These repetitive noise events would normally classify the site as "too noisy" for any advanced earthquake research.</p><p>With the real-time open database from Wiener Linien it is possible to attribute many of the repetitive seismic signals (e.g. on a Raspberry Shake Citizen Science Station) to the surrounding trams and train lines. The detection challenge was initiated in a Citizen Science Hackathon, where public interest sparked this research. The available train schedule and more than one year of continuous seismic records is sufficient to train and test a machine learning classifier which finds most characteristic features in the signals of commuter trains and trams, such as the energy in each frequency band.</p><p>The labeled dataset can be used to train our detection algorithm to find similar signals and to help determine whether a certain signal is present or not. An additional second seismic Raspberry Shake sensor is installed in the vicinity, to further constrain the directionality of the trains.</p><p>Studying the vibrations of train signals and solving the classification task of these repetitive patterns first can help develop robust methods<br>for seismically loud environments, and might lead to the detection of lower magnitude events such as regional earthquakes or landslides.&#160;</p>
Many potential applications of artificial intelligence involve making real-time decisions in physical systems. Automobile racing represents an extreme case of real-time decision making in close proximity to other highly-skilled drivers while near the limits of vehicular control. Racing simulations, such as the PlayStation game Gran Turismo, faithfully reproduce the nonlinear control challenges of real race cars while also encapsulating the complex multi-agent interactions. We attack, and solve for the first time, the simulated racing challenge using model-free deep reinforcement learning. We introduce a novel reinforcement learning algorithm and enhance the learning process with mixed scenario training to encourage the agent to incorporate racing tactics into an integrated control policy. In addition, we construct a reward function that enables the agent to adhere to the sport's under-specified racing etiquette rules. We demonstrate the capabilities of our agent, GT Sophy, by winning two of three races against four of the world's best Gran Turismo drivers and being competitive in the overall team score. By showing that these techniques can be successfully used to train championship-level race car drivers, we open up the possibility of their use in other complex dynamical systems and real-world applications.
<p>Any time series can be represented as a sum of sine waves with the help of the Fourier transform. But such a transformation doesn&#8217;t answer whether the signal is coming from one source or several; neither it allows separation of such sources. In this work, we present a technique from the Machine Learning domain, called Auto-encoders that utilizes the ability of the neural network to generate signals from the latent space, which in turn allows us to identify signals from an arbitrary number of sources and can generate them as separate waveforms without any loss. We took ground motion records of passing trains and trams in the vicinity of the University of Vienna and trained the network to produce &#8220;clean&#8221; individual signals from &#8220;mixed&#8221; waveforms. This work proves the concept and steers the direction for further research of earthquake-induced source separation. It also benefits interference seismometry, since &#8220;noise&#8221; used for such research can be separated from the signal, thus reducing manual processing (cutting and clipping signals) of seismic records.&#160;</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.