PyTorchKR Papers

최신 논문

총 85편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2309.00296

End-to-end Lidar-Driven Reinforcement Learning for Autonomous Racing

Reinforcement Learning (RL) has emerged as a transformative approach in the domains of automation and robotics, offering powerful solutions to complex problems that conventional methods struggle to address. In scenarios where the problem definitions are elusive and challenging to quantify, learning-based solutions such as RL become particularly valuable. One instance of such complexity can be found in the realm of car racing, a dynamic and unpredictable environment that demands sophisticated decision-making algorithms. This study focuses on developing and training an RL agent to navigate a racing environment solely using feedforward raw lidar and velocity data in a simulated context. The agent's performance, trained in the simulation environment, is then experimentally evaluated in a real-world racing scenario. This exploration underlines the feasibility and potential benefits of RL algorithm enhancing autonomous racing performance, especially in the environments where prior map information is not available.

arXiv:2308.13491

Towards Optimal Head-to-head Autonomous Racing with Curriculum Reinforcement Learning

Head-to-head autonomous racing is a challenging problem, as the vehicle needs to operate at the friction or handling limits in order to achieve minimum lap times while also actively looking for strategies to overtake/stay ahead of the opponent. In this work we propose a head-to-head racing environment for reinforcement learning which accurately models vehicle dynamics. Some previous works have tried learning a policy directly in the complex vehicle dynamics environment but have failed to learn an optimal policy. In this work, we propose a curriculum learning-based framework by transitioning from a simpler vehicle model to a more complex real environment to teach the reinforcement learning agent a policy closer to the optimal policy. We also propose a control barrier function-based safe reinforcement learning algorithm to enforce the safety of the agent in a more effective way while not compromising on optimality.

arXiv:2307.07083

A Scenario-Based Functional Testing Approach to Improving DNN Performance

This paper proposes a scenario-based functional testing approach for enhancing the performance of machine learning (ML) applications. The proposed method is an iterative process that starts with testing the ML model on various scenarios to identify areas of weakness. It follows by a further testing on the suspected weak scenarios and statistically evaluate the model's performance on the scenarios to confirm the diagnosis. Once the diagnosis of weak scenarios is confirmed by test results, the treatment of the model is performed by retraining the model using a transfer learning technique with the original model as the base and applying a set of training data specifically targeting the treated scenarios plus a subset of training data selected at random from the original train dataset to prevent the so-call catastrophic forgetting effect. Finally, after the treatment, the model is assessed and evaluated again by testing on the treated scenarios as well as other scenarios to check if the treatment is effective and no side effect caused. The paper reports a case study with a real ML deep neural network (DNN) model, which is the perception system of an autonomous racing car. It is demonstrated that the method is effective in the sense that DNN model's performance can be improved. It provides an efficient method of enhancing ML model's performance with much less human and compute resource than retrain from scratch.

arXiv:2306.08388

Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning

Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills, i.e. sequences of primitive actions. Typically, a skill latent space and policy are discovered from offline data. However, the resulting low-level policy can be unreliable due to low-coverage demonstrations or distribution shifts. As a solution, we propose the Skill-Critic algorithm to fine-tune the low-level policy in conjunction with high-level skill selection. Our Skill-Critic algorithm optimizes both the low-level and high-level policies; these policies are initialized and regularized by the latent space learned from offline demonstrations to guide the parallel policy optimization. We validate Skill-Critic in multiple sparse-reward RL environments, including a new sparse-reward autonomous racing task in Gran Turismo Sport. The experiments show that Skill-Critic's low-level policy fine-tuning and demonstration-guided regularization are essential for good performance. Code and videos are available at our website: https://sites.google.com/view/skill-critic.

arXiv:2306.03405

Vehicle Dynamics Modeling for Autonomous Racing Using Gaussian Processes

Autonomous racing is increasingly becoming a proving ground for autonomous vehicle technology at the limits of its current capabilities. The most prominent examples include the F1Tenth racing series, Formula Student Driverless (FSD), Roborace, and the Indy Autonomous Challenge (IAC). Especially necessary, in high speed autonomous racing, is the knowledge of accurate racecar vehicle dynamics. The choice of the vehicle dynamics model has to be made by balancing the increasing computational demands in contrast to improved accuracy of more complex models. Recent studies have explored learning-based methods, such as Gaussian Process (GP) regression for approximating the vehicle dynamics model. However, these efforts focus on higher level constructs such as motion planning, or predictive control and lack both in realism and rigor of the GP modeling process, which is often over-simplified. This paper presents the most detailed analysis of the applicability of GP models for approximating vehicle dynamics for autonomous racing. In particular we construct dynamic, and extended kinematic models for the popular F1TENTH racing platform. We investigate the effect of kernel choices, sample sizes, racetrack layout, racing lines, and velocity profiles on the efficacy and generalizability of the learned dynamics. We conduct 400+ simulations on real F1 track layouts to provide comprehensive recommendations to the research community for training accurate GP regression for single-track vehicle dynamics of a racecar.

arXiv:2305.04750

Sense, Imagine, Act: Multimodal Perception Improves Model-Based Reinforcement Learning for Head-to-Head Autonomous Racing

Model-based reinforcement learning (MBRL) techniques have recently yielded promising results for real-world autonomous racing using high-dimensional observations. MBRL agents, such as Dreamer, solve long-horizon tasks by building a world model and planning actions by latent imagination. This approach involves explicitly learning a model of the system dynamics and using it to learn the optimal policy for continuous control over multiple timesteps. As a result, MBRL agents may converge to sub-optimal policies if the world model is inaccurate. To improve state estimation for autonomous racing, this paper proposes a self-supervised sensor fusion technique that combines egocentric LiDAR and RGB camera observations collected from the F1TENTH Gym. The zero-shot performance of MBRL agents is empirically evaluated on unseen tracks and against a dynamic obstacle. This paper illustrates that multimodal perception improves robustness of the world model without requiring additional training data. The resulting multimodal Dreamer agent safely avoided collisions and won the most races compared to other tested baselines in zero-shot head-to-head autonomous racing.

arXiv:2305.00579

RAPID: Autonomous Multi-Agent Racing using Constrained Potential Dynamic Games

In this work, we consider the problem of autonomous racing with multiple agents where agents must interact closely and influence each other to compete. We model interactions among agents through a game-theoretical framework and propose an efficient algorithm for tractably solving the resulting game in real time. More specifically, we capture interactions among multiple agents through a constrained dynamic game. We show that the resulting dynamic game is an instance of a simple-to-analyze class of games. Namely, we show that our racing game is an instance of a constrained dynamic potential game. An important and appealing property of dynamic potential games is that a generalized Nash equilibrium of the underlying game can be computed by solving a single constrained optimal control problem instead of multiple coupled constrained optimal control problems. Leveraging this property, we show that the problem of autonomous racing is greatly simplified and develop RAPID (autonomous multi-agent RAcing using constrained PotentIal Dynamic games), a racing algorithm that can be solved tractably in real-time. Through simulation studies, we demonstrate that our algorithm outperforms the state-of-the-art approach. We further show the real-time capabilities of our algorithm in hardware experiments.

arXiv:2303.00638공식 코드 · Papers with Code

MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts

Imitation learning has been widely applied to various autonomous systems thanks to recent development in interactive algorithms that address covariate shift and compounding errors induced by traditional approaches like behavior cloning. However, existing interactive imitation learning methods assume access to one perfect expert. Whereas in reality, it is more likely to have multiple imperfect experts instead. In this paper, we propose MEGA-DAgger, a new DAgger variant that is suitable for interactive learning with multiple imperfect experts. First, unsafe demonstrations are filtered while aggregating the training data, so the imperfect demonstrations have little influence when training the novice policy. Next, experts are evaluated and compared on scenarios-specific metrics to resolve the conflicted labels among experts. Through experiments in autonomous racing scenarios, we demonstrate that policy learned using MEGA-DAgger can outperform both experts and policies learned using the state-of-the-art interactive imitation learning algorithms such as Human-Gated DAgger. The supplementary video can be found at \url{https://youtu.be/wPCht31MHrw}.

arXiv:2302.07035공식 코드 · Papers with Code

Residual Policy Learning for Vehicle Control of Autonomous Racing Cars

The development of vehicle controllers for autonomous racing is challenging because racing cars operate at their physical driving limit. Prompted by the demand for improved performance, autonomous racing research has seen the proliferation of machine learning-based controllers. While these approaches show competitive performance, their practical applicability is often limited. Residual policy learning promises to mitigate this drawback by combining classical controllers with learned residual controllers. The critical advantage of residual controllers is their high adaptability parallel to the classical controller's stable behavior. We propose a residual vehicle controller for autonomous racing cars that learns to amend a classical controller for the path-following of racing lines. In an extensive study, performance gains of our approach are evaluated for a simulated car of the F1TENTH autonomous racing series. The evaluation for twelve replicated real-world racetracks shows that the residual controller reduces lap times by an average of 4.55 % compared to a classical controller and even enables lap time gains on unknown racetracks.

arXiv:2302.01060

Physics Constrained Motion Prediction with Uncertainty Quantification

Predicting the motion of dynamic agents is a critical task for guaranteeing the safety of autonomous systems. A particular challenge is that motion prediction algorithms should obey dynamics constraints and quantify prediction uncertainty as a measure of confidence. We present a physics-constrained approach for motion prediction which uses a surrogate dynamical model to ensure that predicted trajectories are dynamically feasible. We propose a two-step integration consisting of intent and trajectory prediction subject to dynamics constraints. We also construct prediction regions that quantify uncertainty and are tailored for autonomous driving by using conformal prediction, a popular statistical tool. Physics Constrained Motion Prediction achieves a 41% better ADE, 56% better FDE, and 19% better IoU over a baseline in experiments using an autonomous racing dataset.

arXiv:2301.01470공식 코드 · Papers with Code

Model Parameter Identification via a Hyperparameter Optimization Scheme for Autonomous Racing Systems

In this letter, we propose a model parameter identification method via a hyperparameter optimization scheme (MI-HPO). Our method adopts an efficient explore-exploit strategy to identify the parameters of dynamic models in a data-driven optimization manner. We utilize our method for model parameter identification of the AV-21, a full-scaled autonomous race vehicle. We then incorporate the optimized parameters for the design of model-based planning and control systems of our platform. In experiments, MI-HPO exhibits more than 13 times faster convergence than traditional parameter identification methods. Furthermore, the parametric models learned via MI-HPO demonstrate good fitness to the given datasets and show generalization ability in unseen dynamic scenarios. We further conduct extensive field tests to validate our model-based system, demonstrating stable obstacle avoidance and high-speed driving up to 217 km/h at the Indianapolis Motor Speedway and Las Vegas Motor Speedway. The source code for our work and videos of the tests are available at https://github.com/hynkis/MI-HPO.

arXiv:2207.11136

Motion Planning and Control for Multi Vehicle Autonomous Racing at High Speeds

This paper presents a multi-layer motion planning and control architecture for autonomous racing, capable of avoiding static obstacles, performing active overtakes, and reaching velocities above 75 $m/s$. The used offline global trajectory generation and the online model predictive controller are highly based on optimization and dynamic models of the vehicle, where the tires and camber effects are represented in an extended version of the basic Pacejka Magic Formula. The proposed single-track model is identified and validated using multi-body motorsport libraries which allow simulating the vehicle dynamics properly, especially useful when real experimental data are missing. The fundamental regularization terms and constraints of the controller are tuned to reduce the rate of change of the inputs while assuring an acceptable velocity and path tracking. The motion planning strategy consists of a Fren\'et-Frame-based planner which considers a forecast of the opponent produced by a Kalman filter. The planner chooses the collision-free path and velocity profile to be tracked on a 3 seconds horizon to realize different goals such as following and overtaking. The proposed solution has been applied on a Dallara AV-21 racecar and tested at oval race tracks achieving lateral accelerations up to 25 $m/s^{2}$.

arXiv:2207.01275

Solving Learn-to-Race Autonomous Racing Challenge by Planning in Latent Space

Learn-to-Race Autonomous Racing Virtual Challenge hosted on www<dot>aicrowd<dot>com platform consisted of two tracks: Single and Multi Camera. Our UniTeam team was among the final winners in the Single Camera track. The agent is required to pass the previously unknown F1-style track in the minimum time with the least amount of off-road driving violations. In our approach, we used the U-Net architecture for road segmentation, variational autocoder for encoding a road binary mask, and a nearest-neighbor search strategy that selects the best action for a given state. Our agent achieved an average speed of 105 km/h on stage 1 (known track) and 73 km/h on stage 2 (unknown track) without any off-road driving violations. Here we present our solution and results.

arXiv:2206.15012

The Edge of Disaster: A Battle Between Autonomous Racing and Safety

Autonomous racing represents a uniquely challenging control environment where agents must act while on the limits of a vehicle's capability in order to set competitive lap times. This places the agent on a knife's edge, with a very small margin between success and loss of control. Pushing towards this limit leads to a practical tension: we want agents to explore the limitations of vehicle control to maximise speed, but inadvertently going past that limit and losing control can cause irreparable damage to the vehicle itself. We provide a model predictive control (MPC) baseline that is able to, in a single lap, safely adapt to an unseen racetrack and achieve competitive lap times. Our approaches efficacy is demonstrated in simulation using the Learn To Race Challenge's environment and metrics.

arXiv:2205.02953

Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing

We present the results of our autonomous racing virtual challenge, based on the newly-released Learn-to-Race (L2R) simulation framework, which seeks to encourage interdisciplinary research in autonomous driving and to help advance the state of the art on a realistic benchmark. Analogous to racing being used to test cutting-edge vehicles, we envision autonomous racing to serve as a particularly challenging proving ground for autonomous agents as: (i) they need to make sub-second, safety-critical decisions in a complex, fast-changing environment; and (ii) both perception and control must be robust to distribution shifts, novel road features, and unseen obstacles. Thus, the main goal of the challenge is to evaluate the joint safety, performance, and generalisation capabilities of reinforcement learning agents on multi-modal perception, through a two-stage process. In the first stage of the challenge, we evaluate an autonomous agent's ability to drive as fast as possible, while adhering to safety constraints. In the second stage, we additionally require the agent to adapt to an unseen racetrack through safe exploration. In this paper, we describe the new L2R Task 2.0 benchmark, with refined metrics and baseline approaches. We also provide an overview of deployment, evaluation, and rankings for the inaugural instance of the L2R Autonomous Racing Virtual Challenge (supported by Carnegie Mellon University, Arrival Ltd., AICrowd, Amazon Web Services, and Honda Research), which officially used the new L2R Task 2.0 benchmark and received over 20,100 views, 437 active participants, 46 teams, and 733 model submissions -- from 88+ unique institutions, in 58+ different countries. Finally, we release leaderboard results from the challenge and provide description of the two top-ranking approaches in cross-domain model transfer, across multiple sensor configurations and simulated races.

arXiv:2204.11797

PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution

3D neural networks are widely used in real-world applications (e.g., AR/VR headsets, self-driving cars). They are required to be fast and accurate; however, limited hardware resources on edge devices make these requirements rather challenging. Previous work processes 3D data using either voxel-based or point-based neural networks, but both types of 3D models are not hardware-efficient due to the large memory footprint and random memory access. In this paper, we study 3D deep learning from the efficiency perspective. We first systematically analyze the bottlenecks of previous 3D methods. We then combine the best from point-based and voxel-based models together and propose a novel hardware-efficient 3D primitive, Point-Voxel Convolution (PVConv). We further enhance this primitive with the sparse convolution to make it more effective in processing large (outdoor) scenes. Based on our designed 3D primitive, we introduce 3D Neural Architecture Search (3D-NAS) to explore the best 3D network architecture given a resource constraint. We evaluate our proposed method on six representative benchmark datasets, achieving state-of-the-art performance with 1.8-23.7x measured speedup. Furthermore, our method has been deployed to the autonomous racing vehicle of MIT Driverless, achieving larger detection range, higher accuracy and lower latency.

arXiv:2202.03807

Indy Autonomous Challenge -- Autonomous Race Cars at the Handling Limits

Motorsport has always been an enabler for technological advancement, and the same applies to the autonomous driving industry. The team TUM Auton-omous Motorsports will participate in the Indy Autonomous Challenge in Octo-ber 2021 to benchmark its self-driving software-stack by racing one out of ten autonomous Dallara AV-21 racecars at the Indianapolis Motor Speedway. The first part of this paper explains the reasons for entering an autonomous vehicle race from an academic perspective: It allows focusing on several edge cases en-countered by autonomous vehicles, such as challenging evasion maneuvers and unstructured scenarios. At the same time, it is inherently safe due to the motor-sport related track safety precautions. It is therefore an ideal testing ground for the development of autonomous driving algorithms capable of mastering the most challenging and rare situations. In addition, we provide insight into our soft-ware development workflow and present our Hardware-in-the-Loop simulation setup. It is capable of running simulations of up to eight autonomous vehicles in real time. The second part of the paper gives a high-level overview of the soft-ware architecture and covers our development priorities in building a high-per-formance autonomous racing software: maximum sensor detection range, relia-ble handling of multi-vehicle situations, as well as reliable motion control under uncertainty.

arXiv:2201.03246

Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing

In an autonomous driving system, perception - identification of features and objects from the environment - is crucial. In autonomous racing, high speeds and small margins demand rapid and accurate detection systems. During the race, the weather can change abruptly, causing significant degradation in perception, resulting in ineffective manoeuvres. In order to improve detection in adverse weather, deep-learning-based models typically require extensive datasets captured in such conditions - the collection of which is a tedious, laborious, and costly process. However, recent developments in CycleGAN architectures allow the synthesis of highly realistic scenes in multiple weather conditions. To this end, we introduce an approach of using synthesised adverse condition datasets in autonomous racing (generated using CycleGAN) to improve the performance of four out of five state-of-the-art detectors by an average of 42.7 and 4.4 mAP percentage points in the presence of night-time conditions and droplets, respectively. Furthermore, we present a comparative analysis of five object detectors - identifying the optimal pairing of detector and training data for use during autonomous racing in challenging conditions.

arXiv:2112.11798공식 코드 · Papers with Code

YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles

As autonomous vehicles and autonomous racing rise in popularity, so does the need for faster and more accurate detectors. While our naked eyes are able to extract contextual information almost instantly, even from far away, image resolution and computational resources limitations make detecting smaller objects (that is, objects that occupy a small pixel area in the input image) a genuinely challenging task for machines and a wide-open research field. This study explores how the popular YOLOv5 object detector can be modified to improve its performance in detecting smaller objects, with a particular application in autonomous racing. To achieve this, we investigate how replacing certain structural elements of the model (as well as their connections and other parameters) can affect performance and inference time. In doing so, we propose a series of models at different scales, which we name `YOLO-Z', and which display an improvement of up to 6.9% in mAP when detecting smaller objects at 50% IOU, at the cost of just a 3ms increase in inference time compared to the original YOLOv5. Our objective is to inform future research on the potential of adjusting a popular detector such as YOLOv5 to address specific tasks and provide insights on how specific changes can impact small object detection. Such findings, applied to the broader context of autonomous vehicles, could increase the amount of contextual information available to such systems.

arXiv:2110.07699

Safe Autonomous Racing via Approximate Reachability on Ego-vision

Racing demands each vehicle to drive at its physical limits, when any safety infraction could lead to catastrophic failure. In this work, we study the problem of safe reinforcement learning (RL) for autonomous racing, using the vehicle's ego-camera view and speed as input. Given the nature of the task, autonomous agents need to be able to 1) identify and avoid unsafe scenarios under the complex vehicle dynamics, and 2) make sub-second decision in a fast-changing environment. To satisfy these criteria, we propose to incorporate Hamilton-Jacobi (HJ) reachability theory, a safety verification method for general non-linear systems, into the constrained Markov decision process (CMDP) framework. HJ reachability not only provides a control-theoretic approach to learn about safety, but also enables low-latency safety verification. Though HJ reachability is traditionally not scalable to high-dimensional systems, we demonstrate that with neural approximation, the HJ safety value can be learned directly on vision context -- the highest-dimensional problem studied via the method, to-date. We evaluate our method on several benchmark tasks, including Safety Gym and Learn-to-Race (L2R), a recently-released high-fidelity autonomous racing environment. Our approach has significantly fewer constraint violations in comparison to other constrained RL baselines in Safety Gym, and achieves the new state-of-the-art results on the L2R benchmark task. We provide additional visualization of agent behavior at the following anonymized paper website: https://sites.google.com/view/safeautonomousracing/home