| 1. |
- Dhar, Abhishek, et al.
(author)
-
Disturbance-Parametrized Robust Lattice-based Motion Planning
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858 .- 2379-8904.
-
Journal article (peer-reviewed)abstract
- This paper introduces a disturbance-parametrized (DP) robust lattice-based motion-planning framework for nonlinear systems affected by bounded disturbances. A key idea in this work is to rigorously exploit the available knowledge about the disturbance, starting already offline at the time when a library of DP motion primitives is computed and ending not before the motion has been executed online. Given an up-to-date-estimate of the disturbance, the lattice-based motion planner performs a graph search online, to non-conservatively compute a disturbance aware optimal motion plan with formally motivated margins to obstacles. This is done utilizing the DP motion primitives, around which tubes are generated utilizing a suitably designed robust controller. The sizes of the tubes are dependent on the upper bounds of the disturbance appearing in the error between the actual system trajectory and the DP nominal trajectory, which in turn along with the overall optimality of the plan is dependant on the user-selected resolution of the available disturbance estimates. Increasing the resolution of the disturbance parameter results in smaller sizes of tubes around the motion primitives and can significantly reduce the conservativeness compared to traditional approaches, thus increasing the performance of the computed motion plans. The proposed strategy is implemented on an Euler-Lagrange-based ship model which is affected by a significant wind disturbance and the efficiency of the strategy is validated through a suitable simulation example.
|
|
| 2. |
- Nielsen, Kristin, 1986-, et al.
(author)
-
Multi-Hypothesis SLAM for Non-Static Environments with Reoccurring Landmarks
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - : IEEE. - 2379-8858 .- 2379-8904. ; 8:4, s. 3191-3203
-
Journal article (peer-reviewed)abstract
- A static world assumption is often used when considering the simultaneous localization and mapping (SLAM) problem. In reality, especially when long-term autonomy is the objective, this is not valid. This paper studies a scenario where uniquely identifiable landmarks can attend multiple discrete positions, not known a priori . Based on a feature based multi-hypothesis map representation, a multi-hypothesis SLAM algorithm is developed inspired by target tracking theory. The creation of such a map is merged into the SLAM framework allowing any available SLAM method to solve the underlying mapping and localization problem for each hypothesis. A recursively updated hypothesis score allows for hypothesis rejection and prevents exponential growth in the number of hypotheses. The developed method is evaluated in an underground mine application, where physical barriers can be moved in between multiple distinct positions. Simulations are conducted in this environment showing the benefits of the multi-hypothesis approach compared to executing a standard SLAM algorithm. Practical considerations as well as suitable approximations are elaborated upon and experiments on real data further validates the simulated results and show that the multi-hypothesis approach has similar performance in reality as in simulation.
|
|
| 3. |
- Teng, Siyu, et al.
(author)
-
Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - : Institute of Electrical and Electronics Engineers (IEEE). - 2379-8858 .- 2379-8904. ; 8:1, s. 673-683
-
Journal article (peer-reviewed)abstract
- End-to-end autonomous driving provides a simple and efficient framework for autonomous driving systems, which can directly obtain control commands from raw perception data. However, it fails to address stability and interpretability problems in complex urban scenarios. In this paper, we construct a two-stage end-to-end autonomous driving model for complex urban scenarios, named HIIL (Hierarchical Interpretable Imitation Learning), which integrates interpretable BEV mask and steering angle to solve the problems shown above. In Stage One, we propose a pretrained Bird's Eye View (BEV) model which leverages a BEV mask to present an interpretation of the surrounding environment. In Stage Two, we construct an Interpretable Imitation Learning (IIL) model that fuses BEV latent feature from Stage One with an additional steering angle from Pure-Pursuit (PP) algorithm. In the HIIL model, visual information is converted to semantic images by the semantic segmentation network, and the semantic images are encoded to extract the BEV latent feature, which are decoded to predict BEV masks and fed to the IIL as perception data. In this way, the BEV latent feature bridges the BEV and IIL models. Visual information can be supplemented by the calculated steering angle for PP algorithm, speed vector, and location information, thus it could have better performance in complex and terrible scenarios. Our HIIL model meets an urgent requirement for interpretability and robustness of autonomous driving. We validate the proposed model in the CARLA simulator with extensive experiments which show remarkable interpretability, generalization, and robustness capability in unknown scenarios for navigation tasks.
|
|
| 4. |
- Westny, Theodor, 1993-, et al.
(author)
-
MTP-GO : Graph-Based Probabilistic Multi-Agent Trajectory Prediction With Neural ODEs
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - : IEEE. - 2379-8858 .- 2379-8904. ; 8:9, s. 4223-4236
-
Journal article (peer-reviewed)abstract
- Enabling resilient autonomous motion planning requires robust predictions of surrounding road users’ future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of metrics.
|
|
| 5. |
- Dahl, John, 1986, et al.
(author)
-
Prediction-Uncertainty-Aware Threat Detection for ADAS: A Case Study on Lane-Keeping Assistance
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858. ; 8:4, s. 2914-2925
-
Journal article (peer-reviewed)abstract
- Advanced driver assistance systems typically support the driver in cases where the driver is likely to fail the driving task. The challenge, from a system perspective, is to accurately detect those cases. Recently, machine learning-based prediction models that are able to estimate the prediction uncertainty in real-time have successfully been introduced for this purpose. However, very little effort has been made on using the prediction uncertainty in the decision-making logic to improve the system's robustness, especially in cases where the input data is affected by noise or anomalies that are not presented in the training data. In this work, four threat-detection methods using uncertainty estimates are proposed and evaluated using a real-world data set. The methods use different strategies for leveraging uncertainty information, where the goal is to ensure that the intervention decision is based on trustworthy predictions. The threat-detection methods' performances are evaluated, using five different learning-based prediction models, in the context of a lane-keeping assistance application.
|
|
| 6. |
- Liu, Jianan, et al.
(author)
-
Deep Instance Segmentation with Automotive Radar Detection Points
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858. ; 8:1, s. 84-94
-
Journal article (peer-reviewed)abstract
- Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points. With the development of automotive radar technologies in recent years, instance segmentation becomes possible by using automotive radar. Its data contain contexts such as radar cross section and micro-Doppler effects, and sometimes can provide detection when the field of view is obscured. The outcome from instance segmentation could be potentially used as the input of trackers for tracking targets. The existing methods often utilize a clustering-based classification framework, which fits the need of real-time processing but has limited performance due to minimum information provided by sparse radar detection points. In this paper, we propose an efficient method based on clustering of estimated semantic information to achieve instance segmentation for the sparse radar detection points. In addition, we show that the performance of the proposed approach can be further enhanced by incorporating the visual multi-layer perceptron. The effectiveness of the proposed method is verified by experimental results on the popular RadarScenes dataset, achieving 89.53% mean coverage and 86.97% mean average precision with the IoU threshold of 0.5, which is superior to other approaches in the literature. More significantly, the consumed memory is around 1MB, and the inference time is less than 40ms, indicating that our proposed algorithm is storage and time efficient. These two criteria ensure the practicality of the proposed method in real-world systems.
|
|
| 7. |
- Liu, Jianan, et al.
(author)
-
GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858. ; 8:2, s. 1176-1189
-
Journal article (peer-reviewed)abstract
- Multi-object tracking (MOT) is among crucial applications in modern advanced driver assistance systems (ADAS) and autonomous driving (AD) systems. The global nearest neighbor (GNN) filter, as the earliest random vector-based Bayesian tracking framework, has been adopted in most of state-of-the-arts trackers in the automotive industry. The development of random finite set (RFS) theory facilitates a mathematically rigorous treatment of the MOT problem, and different variants of RFS-based Bayesian filters have then been proposed. However, their effectiveness in the real ADAS and AD application is still an open problem. In this paper, it is demonstrated that the latest RFS-based Bayesian tracking framework could be superior to typical random vector-based Bayesian tracking framework via a systematic comparative study of both traditional random vector-based Bayesian filters with rule-based heuristic track maintenance and RFS-based Bayesian filters on the nuScenes validation dataset. An RFS-based tracker, namely Poisson multi-Bernoulli filter using the global nearest neighbor (GNN-PMB), is proposed to LiDAR-based MOT tasks. This GNN-PMB tracker is simple to use, and it achieves competitive results on the nuScenes dataset. Specifically, the proposed GNN-PMB tracker outperforms most state-of-the-art LiDAR-only trackers and LiDAR and camera fusion-based trackers, ranking the $3^{rd}$ among all LiDAR-only trackers on nuScenes 3D tracking challenge leader board 1 1 https://bit.ly/3bQJ2CP at the time of submission. Our code is available at https://github.com/chisyliu/GnnPmbTracker .
|
|
| 8. |
- Selvaraj, Yuvaraj, 1990, et al.
(author)
-
Formal Development of Safe Automated Driving Using Differential Dynamic Logic
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858. ; 8:1, s. 988-1000
-
Journal article (peer-reviewed)abstract
- The challenges in providing convincing arguments for safe and correct behavior of automated driving (AD) systems have so far hindered their widespread commercial deployment. Conventional development approaches such as testing and simulation are limited by non-exhaustive analysis, and can thus not guarantee safety in all possible scenarios. Formal methods can provide mathematical proofs that could be used to produce rigorous evidence to support the safety argument. This paper investigates the use of differential dynamic logic and the deductive verification tool KeYmaera X in the development of an AD feature. Specifically, this paper demonstrates how formal models and safety proofs of different design variants of a Decision & Control module can be used in the safety argument of an in-lane AD feature. In doing so, the assumptions and invariant conditions necessary to guarantee safety are identified, and the paper shows how such an analysis helps during the development process in requirement refinement and formulation of the operational design domain. Furthermore, it is shown how the performance of the different models is formally analyzed exhaustively, in all their allowed behaviors.
|
|
| 9. |
- Shen, Zichao, et al.
(author)
-
Analysis of Driving Behavior in Unprotected Left Turns for Autonomous Vehicles using Ensemble Deep Clustering
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858. ; In Press
-
Journal article (peer-reviewed)abstract
- The advent of autonomous driving technology offers transformative potential in mitigating traffic congestion and enhancing road safety. A particularly challenging aspect of traffic dynamics is the unprotected left turn-a scenario at an intersection where the vehicle intending to turn left does not have a dedicated traffic signal, posing a risk to traffic safety and efficiency. This study investigates the dynamics of unprotected left turns by employing data-driven techniques that analyze multi-vehicle data and trajectory patterns to decode complex interactions and behaviors that occur during this maneuver. Our research targets the subtleties of driver behavior in these situations, employing a novel Ensemble Deep Clustering algorithm that innovatively categorizes driving behaviors based on a combination of learned representations and clustering advancements. The deep clustering component involves an iterative process that refines behavioral categorization, while the ensemble technique enhances the precision of these determinations. Using the INTERACTION Dataset, the proposed model is trained and evaluated to offer a better understanding of the intricate driving behaviors in unprotected left turns at intersections. Through the quantitative analysis and comparison with the baseline, we show the superiority of the algorithm, and the results are also interpretable. This methodology can be utilized to improve the decision-making of autonomous vehicles in such scenarios, thus improving the safety of autonomous vehicles, traffic efficiency, and realizing human-robot interaction between autonomous vehicles and drivers.
|
|
| 10. |
- Strandberg, Kim, 1980, et al.
(author)
-
A Systematic Literature Review on Automotive Digital Forensics: Challenges, Technical Solutions and Data Collection
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858. ; 8:2, s. 1350-1367
-
Journal article (peer-reviewed)abstract
- A modern vehicle has a complex internal architecture and is wirelessly connected to the Internet, other vehicles, and the infrastructure. The risk of cyber attacks and other criminal incidents along with recent road accidents caused by autonomous vehicles calls for more research on automotive digital forensics. Failures in automated driving functions can be caused by hardware and software failures and cyber security issues. Thus, it is imperative to be able to determine and investigate the cause of these failures, something which requires trustable data. However, automotive digital forensics is a relatively new field for the automotive where most existing self-monitoring and diagnostic systems in vehicles only monitor safety-related events. To the best of our knowledge, our work is the first systematic literature review on the current research within this field. We identify and assess over 300 papers published between 2006 - 2021 and further map the relevant papers to different categories based on identified focus areas to give a comprehensive overview of the forensics field and the related research activities. Moreover, we identify forensically relevant data from the literature, link the data to categories, and further map them to required security properties and potential stakeholders. Our categorization makes it easy for practitioners and researchers to quickly find relevant work within a particular sub-field of digital forensics. We believe our contributions can guide digital forensic investigations in automotive and similar areas, such as cyber-physical systems and smart cities, facilitate further research, and serve as a guideline for engineers implementing forensics mechanisms.
|
|
| 11. |
- Westny, Theodor, et al.
(author)
-
MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858. ; 8:9, s. 4223-4236
-
Journal article (peer-reviewed)abstract
- Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of metrics.
|
|
| 12. |
- Zhang, Chi, et al.
(author)
-
Spatial-Temporal-Spectral LSTM: A Transferable Model for Pedestrian Trajectory Prediction
- 2023
-
In: IEEE Transactions on Intelligent Vehicles. - 2379-8858.
-
Journal article (peer-reviewed)abstract
- Predicting the trajectories of pedestrians is critical for developing safe advanced driver assistance systems and autonomous driving systems. Most existing models for pedestrian trajectory prediction focused on a single dataset without considering the transferability to other previously unseen datasets. This leads to poor performance on new unseen datasets and hinders leveraging off-the-shelf labeled datasets and models. In this paper, we propose a transferable model, namely the “Spatial-Temporal-Spectral (STS) LSTM” model, that represents the motion pattern of pedestrians with spatial, temporal, and spectral domain information. Quantitative results and visualizations indicate that our proposed spatial-temporal-spectral representation enables the model to learn generic motion patterns and improves the performance on both source and target datasets. We reveal the transferability of three commonly used network structures, including long short-term memory networks (LSTMs), convolutional neural networks (CNNs), and Transformers, and employ the LSTM structure with negative log-likelihood loss in our model since it has the best transferability. The proposed STS LSTM model demonstrates good prediction accuracy when transferring to target datasets without any prior knowledge, and has a faster inference speed compared to the state-of-the-art models. Our work addresses the gap in learning knowledge from source datasets and transferring it to target datasets in the field of pedestrian trajectory prediction, and enables the reuse of publicly available off-the-shelf datasets.
|
|
