Alert button

"autonomous cars": models, code, and papers
Alert button

Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning

Jan 09, 2023
Ana Carrasco, João Sequeira

Figure 1 for Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning
Figure 2 for Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning
Figure 3 for Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning
Figure 4 for Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning

This paper proposes an adaptable path tracking control system based on Reinforcement Learning (RL) for autonomous cars. A four-parameter controller shapes the behavior of the vehicle to navigate on lane changes and roundabouts. The tuning of the tracker uses an educated Q-Learning algorithm to minimize the lateral and steering trajectory errors. The CARLA simulation environment was used both for training and testing. The results show the vehicle is able to adapt its behavior to the different types of reference trajectories, navigating safely with low tracking errors. The use of a ROS bridge between the CARLA and the tracker results (i) in a realistic system, and (ii) simplifies the replacement of the CARLA by a real vehicle. An argument on the dependability of the overall architecture based on stability results of non-smooth systems is presented at the end of the paper.

Evaluating the acceptance of autonomous vehicles in the future

Jan 26, 2023
Angel Madridano Carrasco, Delgermaa Gankhuyag, Miguel Angel de Miguel Paraiso, Martin Palos Lorite, Cristina Olaverri-Monreal, Fernando Garcia Fernandez

Figure 1 for Evaluating the acceptance of autonomous vehicles in the future
Figure 2 for Evaluating the acceptance of autonomous vehicles in the future
Figure 3 for Evaluating the acceptance of autonomous vehicles in the future
Figure 4 for Evaluating the acceptance of autonomous vehicles in the future

The continuous advance of the automotive industry is leading to the emergence of more advanced driver assistance systems that enable the automation of certain tasks and that are undoubtedly aimed at achieving vehicles in which the driving task can be completely delegated. All these advances will bring changes in the paradigm of the automotive market, as is the case of insurance. For this reason, CESVIMAP and the Universidad Carlos III de Madrid are working on an Autonomous Testing pLatform for insurAnce reSearch (ATLAS) to study this technology and obtain first-hand knowledge about the responsibilities of each of the agents involved in the development of the vehicles of the future. This work gathers part of the advancements made in ATLAS, which have made it possible to have an autonomous vehicle with which to perform tests in real environments and demonstrations bringing the vehicle closer to future users. As a result of this work, and in collaboration with the Johannes Kepler University Linz, the impact, degree of acceptance and confidence of users in autonomous vehicles has been studied once they have taken a trip on board a fully autonomous vehicle such as ATLAS. This study has found that, while most users would be willing to use an autonomous vehicle, the same users are concerned about the use of this type of technology. Thus, understanding the reasons for this concern can help define the future of autonomous cars.

Barrier-Based Test Synthesis for Safety-Critical Systems Subject to Timed Reach-Avoid Specifications

Jan 23, 2023
Prithvi Akella, Mohamadreza Ahmadi, Richard M. Murray, Aaron D. Ames

Figure 1 for Barrier-Based Test Synthesis for Safety-Critical Systems Subject to Timed Reach-Avoid Specifications
Figure 2 for Barrier-Based Test Synthesis for Safety-Critical Systems Subject to Timed Reach-Avoid Specifications
Figure 3 for Barrier-Based Test Synthesis for Safety-Critical Systems Subject to Timed Reach-Avoid Specifications
Figure 4 for Barrier-Based Test Synthesis for Safety-Critical Systems Subject to Timed Reach-Avoid Specifications

We propose an adversarial, time-varying test-synthesis procedure for safety-critical systems without requiring specific knowledge of the underlying controller steering the system. From a broader test and evaluation context, determination of difficult tests of system behavior is important as these tests would elucidate problematic system phenomena before these mistakes can engender problematic outcomes, e.g. loss of human life in autonomous cars, costly failures for airplane systems, etc. Our approach builds on existing, simulation-based work in the test and evaluation literature by offering a controller-agnostic test-synthesis procedure that provides a series of benchmark tests with which to determine controller reliability. To achieve this, our approach codifies the system objective as a timed reach-avoid specification. Then, by coupling control barrier functions with this class of specifications, we construct an instantaneous difficulty metric whose minimizer corresponds to the most difficult test at that system state. We use this instantaneous difficulty metric in a game-theoretic fashion, to produce an adversarial, time-varying test-synthesis procedure that does not require specific knowledge of the system's controller, but can still provably identify realizable and maximally difficult tests of system behavior. Finally, we develop this test-synthesis procedure for both continuous and discrete-time systems and showcase our test-synthesis procedure on simulated and hardware examples.

Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modelling

Dec 10, 2022
Zhaoning Li, Qiaoli Jiang, Zhengming Wu, Anqi Liu, Haiyan Wu, Miner Huang, Kai Huang, Yixuan Ku

Figure 1 for Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modelling
Figure 2 for Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modelling
Figure 3 for Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modelling
Figure 4 for Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modelling

Autonomous cars are indispensable when humans go further down the hands-free route. Although existing literature highlights that the acceptance of the autonomous car will increase if it drives in a human-like manner, sparse research offers the naturalistic experience from a passenger's seat perspective to examine the human likeness of current autonomous cars. The present study tested whether the AI driver could create a human-like ride experience for passengers based on 69 participants' feedback in a real-road scenario. We designed a ride experience-based version of the non-verbal Turing test for automated driving. Participants rode in autonomous cars (driven by either human or AI drivers) as a passenger and judged whether the driver was human or AI. The AI driver failed to pass our test because passengers detected the AI driver above chance. In contrast, when the human driver drove the car, the passengers' judgement was around chance. We further investigated how human passengers ascribe humanness in our test. Based on Lewin's field theory, we advanced a computational model combining signal detection theory with pre-trained language models to predict passengers' humanness rating behaviour. We employed affective transition between pre-study baseline emotions and corresponding post-stage emotions as the signal strength of our model. Results showed that the passengers' ascription of humanness would increase with the greater affective transition. Our study suggested an important role of affective transition in passengers' ascription of humanness, which might become a future direction for autonomous driving.

* 16 pages, 9 figures, 3 tables 

StyleID: Identity Disentanglement for Anonymizing Faces

Dec 28, 2022
Minh-Ha Le, Niklas Carlsson

Figure 1 for StyleID: Identity Disentanglement for Anonymizing Faces
Figure 2 for StyleID: Identity Disentanglement for Anonymizing Faces
Figure 3 for StyleID: Identity Disentanglement for Anonymizing Faces
Figure 4 for StyleID: Identity Disentanglement for Anonymizing Faces

Privacy of machine learning models is one of the remaining challenges that hinder the broad adoption of Artificial Intelligent (AI). This paper considers this problem in the context of image datasets containing faces. Anonymization of such datasets is becoming increasingly important due to their central role in the training of autonomous cars, for example, and the vast amount of data generated by surveillance systems. While most prior work de-identifies facial images by modifying identity features in pixel space, we instead project the image onto the latent space of a Generative Adversarial Network (GAN) model, find the features that provide the biggest identity disentanglement, and then manipulate these features in latent space, pixel space, or both. The main contribution of the paper is the design of a feature-preserving anonymization framework, StyleID, which protects the individuals' identity, while preserving as many characteristics of the original faces in the image dataset as possible. As part of the contribution, we present a novel disentanglement metric, three complementing disentanglement methods, and new insights into identity disentanglement. StyleID provides tunable privacy, has low computational complexity, and is shown to outperform current state-of-the-art solutions.

* Accepted to Privacy Enhancing Technologies Symposium (PETS), July 2023. Will appear in Proceedings on Privacy Enhancing Technologies (PoPETs), volume 1, 2023. 15 pages including references and appendix, 16 figures, 5 tables 

Advising Autonomous Cars about the Rules of the Road

Sep 28, 2022
Joe Collenette, Louise A. Dennis, Michael Fisher

Figure 1 for Advising Autonomous Cars about the Rules of the Road
Figure 2 for Advising Autonomous Cars about the Rules of the Road

This paper describes (R)ules (o)f (T)he (R)oad (A)dvisor, an agent that provides recommended and possible actions to be generated from a set of human-level rules. We describe the architecture and design of RoTRA, both formally and with an example. Specifically, we use RoTRA to formalise and implement the UK "Rules of the Road", and describe how this can be incorporated into autonomous cars such that they can reason internally about obeying the rules of the road. In addition, the possible actions generated are annotated to indicate whether the rules state that the action must be taken or that they only recommend that the action should be taken, as per the UK Highway Code (Rules of The Road). The benefits of utilising this system include being able to adapt to different regulations in different jurisdictions; allowing clear traceability from rules to behaviour, and providing an external automated accountability mechanism that can check whether the rules were obeyed in some given situation. A simulation of an autonomous car shows, via a concrete example, how trust can be built by putting the autonomous vehicle through a number of scenarios which test the car's ability to obey the rules of the road. Autonomous cars that incorporate this system are able to ensure that they are obeying the rules of the road and external (legal or regulatory) bodies can verify that this is the case, without the vehicle or its manufacturer having to expose their source code or make their working transparent, thus allowing greater trust between car companies, jurisdictions, and the general public.

* EPTCS 371, 2022, pp. 62-76  
* In Proceedings FMAS2022 ASYDE2022, arXiv:2209.13181 

AmbieGen: A Search-based Framework for Autonomous Systems Testing

Jan 01, 2023
Dmytro Humeniuk, Foutse Khomh, Giuliano Antoniol

Figure 1 for AmbieGen: A Search-based Framework for Autonomous Systems Testing
Figure 2 for AmbieGen: A Search-based Framework for Autonomous Systems Testing
Figure 3 for AmbieGen: A Search-based Framework for Autonomous Systems Testing
Figure 4 for AmbieGen: A Search-based Framework for Autonomous Systems Testing

Thorough testing of safety-critical autonomous systems, such as self-driving cars, autonomous robots, and drones, is essential for detecting potential failures before deployment. One crucial testing stage is model-in-the-loop testing, where the system model is evaluated by executing various scenarios in a simulator. However, the search space of possible parameters defining these test scenarios is vast, and simulating all combinations is computationally infeasible. To address this challenge, we introduce AmbieGen, a search-based test case generation framework for autonomous systems. AmbieGen uses evolutionary search to identify the most critical scenarios for a given system, and has a modular architecture that allows for the addition of new systems under test, algorithms, and search operators. Currently, AmbieGen supports test case generation for autonomous robots and autonomous car lane keeping assist systems. In this paper, we provide a high-level overview of the framework's architecture and demonstrate its practical use cases.

* 17 pages, 10 figures 

REAP: A Large-Scale Realistic Adversarial Patch Benchmark

Dec 12, 2022
Nabeel Hingun, Chawin Sitawarin, Jerry Li, David Wagner

Figure 1 for REAP: A Large-Scale Realistic Adversarial Patch Benchmark
Figure 2 for REAP: A Large-Scale Realistic Adversarial Patch Benchmark
Figure 3 for REAP: A Large-Scale Realistic Adversarial Patch Benchmark
Figure 4 for REAP: A Large-Scale Realistic Adversarial Patch Benchmark

Machine learning models are known to be susceptible to adversarial perturbation. One famous attack is the adversarial patch, a sticker with a particularly crafted pattern that makes the model incorrectly predict the object it is placed on. This attack presents a critical threat to cyber-physical systems that rely on cameras such as autonomous cars. Despite the significance of the problem, conducting research in this setting has been difficult; evaluating attacks and defenses in the real world is exceptionally costly while synthetic data are unrealistic. In this work, we propose the REAP (REalistic Adversarial Patch) benchmark, a digital benchmark that allows the user to evaluate patch attacks on real images, and under real-world conditions. Built on top of the Mapillary Vistas dataset, our benchmark contains over 14,000 traffic signs. Each sign is augmented with a pair of geometric and lighting transformations, which can be used to apply a digitally generated patch realistically onto the sign. Using our benchmark, we perform the first large-scale assessments of adversarial patch attacks under realistic conditions. Our experiments suggest that adversarial patch attacks may present a smaller threat than previously believed and that the success rate of an attack on simpler digital simulations is not predictive of its actual effectiveness in practice. We release our benchmark publicly at https://github.com/wagner-group/reap-benchmark.

* Code and benchmark can be found at https://github.com/wagner-group/reap-benchmark 

TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM

Oct 28, 2022
Nicola Marinello, Marc Proesmans, Luc Van Gool

Figure 1 for TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
Figure 2 for TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
Figure 3 for TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
Figure 4 for TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM

3D object tracking is a critical task in autonomous driving systems. It plays an essential role for the system's awareness about the surrounding environment. At the same time there is an increasing interest in algorithms for autonomous cars that solely rely on inexpensive sensors, such as cameras. In this paper we investigate the use of triplet embeddings in combination with motion representations for 3D object tracking. We start from an off-the-shelf 3D object detector, and apply a tracking mechanism where objects are matched by an affinity score computed on local object feature embeddings and motion descriptors. The feature embeddings are trained to include information about the visual appearance and monocular 3D object characteristics, while motion descriptors provide a strong representation of object trajectories. We will show that our approach effectively re-identifies objects, and also behaves reliably and accurately in case of occlusions, missed detections and can detect re-appearance across different field of views. Experimental evaluation shows that our approach outperforms state-of-the-art on nuScenes by a large margin. We also obtain competitive results on KITTI.

* Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops June 2022 4500-4510  
* Accepted to CVPR 2022 Workshop on Autonomous Driving