PyTorchKR Papers

최신 논문

총 2,663편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2301.10077

Autonomous particles

Consider a reinforcement learning problem where an agent has access to a very large amount of information about the environment, but it can only take very few actions to accomplish its task and to maximize its reward. Evidently, the main problem for the agent is to learn a map from a very high-dimensional space (which represents its environment) to a very low-dimensional space (which represents its actions). The high-to-low dimensional map implies that most of the information about the environment is irrelevant for the actions to be taken, and only a small fraction of information is relevant. In this paper we argue that the relevant information need not be learned by brute force (which is the standard approach), but can be identified from the intrinsic symmetries of the system. We analyze in details a reinforcement learning problem of autonomous driving, where the corresponding symmetry is the Galilean symmetry, and argue that the learning task can be accomplished with very few relevant parameters, or, more precisely, invariants. For a numerical demonstration, we show that the autonomous vehicles (which we call autonomous particles since they describe very primitive vehicles) need only four relevant invariants to learn how to drive very well without colliding with other particles. The simple model can be easily generalized to include different types of particles (e.g. for cars, for pedestrians, for buildings, for road signs, etc.) with different types of relevant invariants describing interactions between them. We also argue that there must exist a field theory description of the learning system where autonomous particles would be described by fermionic degrees of freedom and interactions mediated by the relevant invariants would be described by bosonic degrees of freedom.

arXiv:2301.09420

On Multi-Agent Deep Deterministic Policy Gradients and their Explainability for SMARTS Environment

Multi-Agent RL or MARL is one of the complex problems in Autonomous Driving literature that hampers the release of fully-autonomous vehicles today. Several simulators have been in iteration after their inception to mitigate the problem of complex scenarios with multiple agents in Autonomous Driving. One such simulator--SMARTS, discusses the importance of cooperative multi-agent learning. For this problem, we discuss two approaches--MAPPO and MADDPG, which are based on-policy and off-policy RL approaches. We compare our results with the state-of-the-art results for this challenge and discuss the potential areas of improvement while discussing the explainability of these approaches in conjunction with waypoints in the SMARTS environment.

arXiv:2301.08957

Slice Transformer and Self-supervised Learning for 6DoF Localization in 3D Point Cloud Maps

Precise localization is critical for autonomous vehicles. We present a self-supervised learning method that employs Transformers for the first time for the task of outdoor localization using LiDAR data. We propose a pre-text task that reorganizes the slices of a $360^\circ$ LiDAR scan to leverage its axial properties. Our model, called Slice Transformer, employs multi-head attention while systematically processing the slices. To the best of our knowledge, this is the first instance of leveraging multi-head attention for outdoor point clouds. We additionally introduce the Perth-WA dataset, which provides a large-scale LiDAR map of Perth city in Western Australia, covering $\sim$4km$^2$ area. Localization annotations are provided for Perth-WA. The proposed localization method is thoroughly evaluated on Perth-WA and Appollo-SouthBay datasets. We also establish the efficacy of our self-supervised learning approach for the common downstream task of object classification using ModelNet40 and ScanNN datasets. The code and Perth-WA data will be publicly released.

arXiv:2301.08595

MAVERIC: A Data-Driven Approach to Personalized Autonomous Driving

Personalization of autonomous vehicles (AV) may significantly increase trust, use, and acceptance. In particular, we hypothesize that the similarity of an AV's driving style compared to the end-user's driving style will have a major impact on end-user's willingness to use the AV. To investigate the impact of driving style on user acceptance, we 1) develop a data-driven approach to personalize driving style and 2) demonstrate that personalization significantly impacts attitudes towards AVs. Our approach learns a high-level model that tunes low-level controllers to ensure safe and personalized control of the AV. The key to our approach is learning an informative, personalized embedding that represents a user's driving style. Our framework is capable of calibrating the level of aggression so as to optimize driving style based upon driver preference. Across two human subject studies (n = 54), we first demonstrate our approach mimics the driving styles of end-users and can tune attributes of style (e.g., aggressiveness). Second, we investigate the factors (e.g., trust, personality etc.) that impact homophily, i.e. an individual's preference for a driving style similar to their own. We find that our approach generates driving styles consistent with end-user styles (p<.001) and participants rate our approach as more similar to their level of aggressiveness (p=.002). We find that personality (p<.001), perceived similarity (p<.001), and high-velocity driving style (p=.0031) significantly modulate the effect of homophily.

arXiv:2301.07636

Generative AI-empowered Effective Physical-Virtual Synchronization in the Vehicular Metaverse

Metaverse seamlessly blends the physical world and virtual space via ubiquitous communication and computing infrastructure. In transportation systems, the vehicular Metaverse can provide a fully-immersive and hyperreal traveling experience (e.g., via augmented reality head-up displays, AR-HUDs) to drivers and users in autonomous vehicles (AVs) via roadside units (RSUs). However, provisioning real-time and immersive services necessitates effective physical-virtual synchronization between physical and virtual entities, i.e., AVs and Metaverse AR recommenders (MARs). In this paper, we propose a generative AI-empowered physical-virtual synchronization framework for the vehicular Metaverse. In physical-to-virtual synchronization, digital twin (DT) tasks generated by AVs are offloaded for execution in RSU with future route generation. In virtual-to-physical synchronization, MARs customize diverse and personal AR recommendations via generative AI models based on user preferences. Furthermore, we propose a multi-task enhanced auction-based mechanism to match and price AVs and MARs for RSUs to provision real-time and effective services. Finally, property analysis and experimental results demonstrate that the proposed mechanism is strategy-proof and adverse-selection free while increasing social surplus by 50%.

arXiv:2301.06863공식 코드 · Papers with Code

A reinforcement learning path planning approach for range-only underwater target localization with autonomous vehicles

Underwater target localization using range-only and single-beacon (ROSB) techniques with autonomous vehicles has been used recently to improve the limitations of more complex methods, such as long baseline and ultra-short baseline systems. Nonetheless, in ROSB target localization methods, the trajectory of the tracking vehicle near the localized target plays an important role in obtaining the best accuracy of the predicted target position. Here, we investigate a Reinforcement Learning (RL) approach to find the optimal path that an autonomous vehicle should follow in order to increase and optimize the overall accuracy of the predicted target localization, while reducing time and power consumption. To accomplish this objective, different experimental tests have been designed using state-of-the-art deep RL algorithms. Our study also compares the results obtained with the analytical Fisher information matrix approach used in previous studies. The results revealed that the policy learned by the RL agent outperforms trajectories based on these analytical solutions, e.g. the median predicted error at the beginning of the target's localisation is 17% less. These findings suggest that using deep RL for localizing acoustic targets could be successfully applied to in-water applications that include tracking of acoustically tagged marine animals by autonomous underwater vehicles. This is envisioned as a first necessary step to validate the use of RL to tackle such problems, which could be used later on in a more complex scenarios

arXiv:2301.05294공식 코드 · Papers with Code

Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections

Intersections are essential road infrastructures for traffic in modern metropolises. However, they can also be the bottleneck of traffic flows as a result of traffic incidents or the absence of traffic coordination mechanisms such as traffic lights. Recently, various control and coordination mechanisms that are beyond traditional control methods have been proposed to improve the efficiency of intersection traffic by leveraging the ability of autonomous vehicles. Amongst these methods, the control of foreseeable mixed traffic that consists of human-driven vehicles (HVs) and robot vehicles (RVs) has emerged. We propose a decentralized multi-agent reinforcement learning approach for the control and coordination of mixed traffic by RVs at real-world, complex intersections -- an open challenge to date. We design comprehensive experiments to evaluate the effectiveness, robustness, generalizablility, and adaptability of our approach. In particular, our method can prevent congestion formation via merely 5% RVs under a real-world traffic demand of 700 vehicles per hour. In contrast, without RVs, congestion will form when the traffic demand reaches as low as 200 vehicles per hour. Moreover, when the RV penetration rate exceeds 60%, our method starts to outperform traffic signal control in terms of the average waiting time of all vehicles. Our method is not only robust against blackout events, sudden RV percentage drops, and V2V communication error, but also enjoys excellent generalizablility, evidenced by its successful deployment in five unseen intersections. Lastly, our method performs well under various traffic rules, demonstrating its adaptability to diverse scenarios. Videos and code of our work are available at https://sites.google.com/view/mixedtrafficcontrol

arXiv:2301.04043

Integrated Analysis of Coarse-Grained Guidance for Traffic Flow Stability

Autonomous vehicles (AVs) enable more efficient and sustainable transportation systems. Ample studies have shown that controlling a small fraction of AVs can smooth traffic flow and mitigate traffic congestion. However, deploying AVs in real-world systems poses challenges due to safety and cost concerns. A viable alternative approach that can be implemented in the near future is $\textit{coarse-grained guidance}$, where human drivers are guided by real-time instructions, updated every $\Delta$ seconds, to stabilize the traffic. While previous theoretical studies consider stability analysis for continuous AV control, this article presents the first integrated theoretical analysis that directly relates the guidance provided to the human drivers to the traffic flow stability outcome. Casting the problem into the Lyapunov stability framework, this study derives sufficient conditions for coarse-grained guidance with hold length $\Delta$ to stabilize the system, and provides extensions of the analysis to incorporate additional human driving behaviors such as magnitude error and reaction delay. Numerical simulations reveal that the theoretical analysis closely matches simulated results. The analysis further offers insights into the relationship between system parameter and stability criteria, and can be leveraged to design improved controllers with greater maximum hold length.

arXiv:2301.01250

Decentralized cooperative perception for autonomous vehicles: Learning to value the unknown

Recently, we have been witnesses of accidents involving autonomous vehicles and their lack of sufficient information. One way to tackle this issue is to benefit from the perception of different view points, namely cooperative perception. We propose here a decentralized collaboration, i.e. peer-to-peer, in which the agents are active in their quest for full perception by asking for specific areas in their surroundings on which they would like to know more. Ultimately, we want to optimize a trade-off between the maximization of knowledge about moving objects and the minimization of the total volume of information received from others, to limit communication costs and message processing time. For this, we propose a way to learn a communication policy that reverses the usual communication paradigm by only requesting from other vehicles what is unknown to the ego-vehicle, instead of filtering on the sender side. We tested three different generative models to be taken as base for a Deep Reinforcement Learning (DRL) algorithm, and compared them to a broadcasting policy and a policy randomly selecting areas. In particular, we propose Locally Predictable VAE (LP-VAE), which appears to be producing better belief states for predictions than state-of-the-art models, both as a standalone model and in the context of DRL. Experiments were conducted in the driving simulator CARLA. Our best models reached on average a gain of 25% of the total complementary information, while only requesting about 5% of the ego-vehicle's perceptual field. This trade-off is adjustable through the interpretable hyperparameters of our reward function.

arXiv:2301.01201공식 코드 · Papers with Code

Uncertainty in Real-Time Semantic Segmentation on Embedded Systems

Application for semantic segmentation models in areas such as autonomous vehicles and human computer interaction require real-time predictive capabilities. The challenges of addressing real-time application is amplified by the need to operate on resource constrained hardware. Whilst development of real-time methods for these platforms has increased, these models are unable to sufficiently reason about uncertainty present when applied on embedded real-time systems. This paper addresses this by combining deep feature extraction from pre-trained models with Bayesian regression and moment propagation for uncertainty aware predictions. We demonstrate how the proposed method can yield meaningful epistemic uncertainty on embedded hardware in real-time whilst maintaining predictive performance.

arXiv:2212.13727

VAFER: Signal Decomposition based Mutual Interference Suppression in FMCW Radars

With increasing application of frequency-modulated continuous wave (FMCW) radars in autonomous vehicles, mutual interference among FMCW radars poses a serious threat. Through this paper, we present a novel approach to effectively and elegantly suppress mutual interference in FMCW radars. We first decompose the received signal into modes using variational mode decomposition (VMD) and perform time-frequency analysis using Fourier synchrosqueezed transform (FSST). The interference-suppressed signal is then reconstructed by applying a proposed energy-entropy-based thresholding operation on the time-frequency spectra of VMD modes. The effectiveness of proposed method is measured in terms of signal-to-interference plus noise ratio (SINR) and correlation coefficient for both simulated and experimental automotive radar data in the presence of FMCW interference. Compared to other existing literature, our proposed method demonstrates significant improvement in the output SINR by at least 14.07 dB for simulated data and 9.87 dB for experimental data.

arXiv:2212.13667

Learning When to Use Adaptive Adversarial Image Perturbations against Autonomous Vehicles

The deep neural network (DNN) models for object detection using camera images are widely adopted in autonomous vehicles. However, DNN models are shown to be susceptible to adversarial image perturbations. In the existing methods of generating the adversarial image perturbations, optimizations take each incoming image frame as the decision variable to generate an image perturbation. Therefore, given a new image, the typically computationally-expensive optimization needs to start over as there is no learning between the independent optimizations. Very few approaches have been developed for attacking online image streams while considering the underlying physical dynamics of autonomous vehicles, their mission, and the environment. We propose a multi-level stochastic optimization framework that monitors an attacker's capability of generating the adversarial perturbations. Based on this capability level, a binary decision attack/not attack is introduced to enhance the effectiveness of the attacker. We evaluate our proposed multi-level image attack framework using simulations for vision-guided autonomous vehicles and actual tests with a small indoor drone in an office environment. The results show our method's capability to generate the image attack in real-time while monitoring when the attacker is proficient given state estimates.

arXiv:2212.12819

Context-Aware Target Classification with Hybrid Gaussian Process prediction for Cooperative Vehicle Safety systems

Vehicle-to-Everything (V2X) communication has been proposed as a potential solution to improve the robustness and safety of autonomous vehicles by improving coordination and removing the barrier of non-line-of-sight sensing. Cooperative Vehicle Safety (CVS) applications are tightly dependent on the reliability of the underneath data system, which can suffer from loss of information due to the inherent issues of their different components, such as sensors failures or the poor performance of V2X technologies under dense communication channel load. Particularly, information loss affects the target classification module and, subsequently, the safety application performance. To enable reliable and robust CVS systems that mitigate the effect of information loss, we proposed a Context-Aware Target Classification (CA-TC) module coupled with a hybrid learning-based predictive modeling technique for CVS systems. The CA-TC consists of two modules: A Context-Aware Map (CAM), and a Hybrid Gaussian Process (HGP) prediction system. Consequently, the vehicle safety applications use the information from the CA-TC, making them more robust and reliable. The CAM leverages vehicles path history, road geometry, tracking, and prediction; and the HGP is utilized to provide accurate vehicles' trajectory predictions to compensate for data loss (due to communication congestion) or sensor measurements' inaccuracies. Based on offline real-world data, we learn a finite bank of driver models that represent the joint dynamics of the vehicle and the drivers' behavior. We combine offline training and online model updates with on-the-fly forecasting to account for new possible driver behaviors. Finally, our framework is validated using simulation and realistic driving scenarios to confirm its potential in enhancing the robustness and reliability of CVS systems.

arXiv:2212.11950

Peek into the Future Camera-based Occupant Sensing in Configurable Cabins for Autonomous Vehicles

The development of fully autonomous vehicles (AVs) can potentially eliminate drivers and introduce unprecedented seating design. However, highly flexible seat configurations may lead to occupants' unconventional poses and actions. Understanding occupant behaviors and prioritize safety features become eye-catching topics in the AV research frontier. Visual sensors have the advantages of cost-efficiency and high-fidelity imaging and become more widely applied for in-car sensing purposes. Occlusion is one big concern for this type of system in crowded car cabins. It is important but largely unknown about how a visual-sensing framework will look like to support 2-D and 3-D human pose tracking towards highly configurable seats. As one of the first studies to touch this topic, we peek into the future camera-based sensing framework via a simulation experiment. Constructed representative car-cabin, seat layouts, and occupant sizes, camera coverage from different angles and positions is simulated and calculated. The comprehensive coverage data are synthesized through an optimization process to determine the camera layout and overall occupant coverage. The results show the needs and design of a different number of cameras to fully or partially cover all the occupants with changeable configurations of up to six seats.

arXiv:2212.11819공식 코드 · Papers with Code

Interaction-Aware Motion Planning for Autonomous Vehicles with Multi-Modal Obstacle Uncertainty Predictions

This paper proposes an interaction and safety-aware motion-planning method for an autonomous vehicle in uncertain multi-vehicle traffic environments. The method integrates the ability of the interaction-aware interacting multiple model Kalman filter (IAIMM-KF) to predict interactive multi-modal maneuvers of surrounding vehicles, and the advantage of model predictive control (MPC) in planning an optimal trajectory in uncertain dynamic environments. The multi-modal prediction uncertainties, containing both the maneuver and trajectory uncertainties of surrounding vehicles, are considered in computing the reference targets and designing the collision-avoidance constraints of MPC for resilient motion planning of the ego vehicle. The MPC achieves safety awareness by incorporating a tunable parameter to adjust the predicted obstacle occupancy in the design of the safety constraints, allowing the approach to achieve a trade-off between performance and robustness. Based on the prediction of the surrounding vehicles, an optimal reference trajectory of the ego vehicle is computed by MPC to follow the time-varying reference targets and avoid collisions with obstacles. The efficiency of the method is illustrated in challenging highway-driving simulation scenarios and a driving scenario from a recorded traffic dataset.

arXiv:2212.10737

Driving Style Recognition at First Impression for Online Trajectory Prediction

This paper proposes a new driving style recognition approach that allows autonomous vehicles (AVs) to perform trajectory predictions for surrounding vehicles with minimal data. Toward that end, we use a hybrid of offline and online methods in the proposed approach. We first learn typical driving styles with PCA and K-means algorithms in the offline part. After that, local Maximum-Likelihood techniques are used to perform online driving style recognition. We benchmarked our method on a real driving dataset against other methods in terms of the RMSE value of the predicted trajectory and the observed trajectory over a 5s duration. The proposed approach can reduce trajectory prediction error by up to 37.7\% compared to using the parameters from other literature and up to 24.4\% compared to not performing driving style recognition.

arXiv:2212.09517

Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensors

Segmentation of lidar data is a task that provides rich, point-wise information about the environment of robots or autonomous vehicles. Currently best performing neural networks for lidar segmentation are fine-tuned to specific datasets. Switching the lidar sensor without retraining on a big set of annotated data from the new sensor creates a domain shift, which causes the network performance to drop drastically. In this work we propose a new method for lidar domain adaption, in which we use annotated panoptic lidar datasets and recreate the recorded scenes in the structure of a different lidar sensor. We narrow the domain gap to the target data by recreating panoptic data from one domain in another and mixing the generated data with parts of (pseudo) labeled target domain data. Our method improves the nuScenes to SemanticKITTI unsupervised domain adaptation performance by 15.2 mean Intersection over Union points (mIoU) and by 48.3 mIoU in our semi-supervised approach. We demonstrate a similar improvement for the SemanticKITTI to nuScenes domain adaptation by 21.8 mIoU and 51.5 mIoU, respectively. We compare our method with two state of the art approaches for semantic lidar segmentation domain adaptation with a significant improvement for unsupervised and semi-supervised domain adaptation. Furthermore we successfully apply our proposed method to two entirely unlabeled datasets of two state of the art lidar sensors Velodyne Alpha Prime and InnovizTwo, and train well performing semantic segmentation networks for both.

arXiv:2212.08800

Cognitive Level-$k$ Meta-Learning for Safe and Pedestrian-Aware Autonomous Driving

The potential market for modern self-driving cars is enormous, as they are developing remarkably rapidly. At the same time, however, accidents of pedestrian fatalities caused by autonomous driving have been recorded in the case of street crossing. To ensure traffic safety in self-driving environments and respond to vehicle-human interaction challenges such as jaywalking, we propose Level-$k$ Meta Reinforcement Learning (LK-MRL) algorithm. It takes into account the cognitive hierarchy of pedestrian responses and enables self-driving vehicles to adapt to various human behaviors. %which takes into account pedestrian responses while learning the optimal strategies. As a self-driving vehicle algorithm, the LK-MRL combines level-$k$ thinking into MAML to prepare for heterogeneous pedestrians and improve intersection safety based on the combination of meta-reinforcement learning and human cognitive hierarchy framework. We evaluate the algorithm in two cognitive confrontation hierarchy scenarios in an urban traffic simulator and illustrate its role in ensuring road safety by demonstrating its capability of conjectural and higher-level reasoning.

arXiv:2212.08539

Predicting Autonomous Vehicle Collision Injury Severity Levels for Ethical Decision Making and Path Planning

Developments in autonomous vehicles (AVs) are rapidly advancing and will in the next 20 years become a central part to our society. However, especially in the early stages of deployment, there is expected to be incidents involving AVs. In the event of AV incidents, decisions will need to be made that require ethical decisions, e.g., deciding between colliding into a group of pedestrians or a rigid barrier. For an AV to undertake such ethical decision making and path planning, simulation models of the situation will be required that are used in real-time on-board the AV. These models will enable path planning and ethical decision making to be undertaken based on predetermined collision injury severity levels. In this research, models are developed for the path planning and ethical decision making that predetermine knowledge regarding the possible collision injury severities, i.e., peak deformation of the AV colliding into the rigid barrier or the impact velocity of the AV colliding into a pedestrian. Based on such knowledge and using fuzzy logic, a novel nonlinear weighted utility cost function for the collision injury severity levels is developed. This allows the model-based predicted collision outcomes arising from AV peak deformation and AV-pedestrian impact velocity to be examined separately via weighted utility cost functions with a common structure. The general form of the weighted utility cost function exploits a fuzzy sets approach, thus allowing common utility costs from the two separate utility cost functions to be meaningfully compared. A decision-making algorithm, which makes use of a utilitarian ethical approach, ensures that the AV will always steer onto the path which represents the lowest injury severity level, hence utility cost to society.

arXiv:2212.08230

An Energy-aware and Fault-tolerant Deep Reinforcement Learning based approach for Multi-agent Patrolling Problems

Autonomous vehicles are suited for continuous area patrolling problems. However, finding an optimal patrolling strategy can be challenging for many reasons. Firstly, patrolling environments are often complex and can include unknown environmental factors, such as wind or landscape. Secondly, autonomous vehicles can have failures or hardware constraints, such as limited battery life. Importantly, patrolling large areas often requires multiple agents that need to collectively coordinate their actions. In this work, we consider these limitations and propose an approach based on model-free, deep multi-agent reinforcement learning. In this approach, the agents are trained to patrol an environment with various unknown dynamics and factors. They can automatically recharge themselves to support continuous collective patrolling. A distributed homogeneous multi-agent architecture is proposed, where all patrolling agents execute identical policies locally based on their local observations and shared location information. This architecture provides a patrolling system that can tolerate agent failures and allow supplementary agents to be added to replace failed agents or to increase the overall patrol performance. The solution is validated through simulation experiments from multiple perspectives, including the overall patrol performance, the efficiency of battery recharging strategies, the overall fault tolerance, and the ability to cooperate with supplementary agents.