Search

The selection of an appropriate control strategy is essential for ensuring safe operation in autonomous driving. While numerous control strategies have been developed for specific driving scenarios, a comprehensive comparative assessment of their performance using the same tuning methodology is lacking in the literature. This paper addresses this gap by presenting a systematic evaluation of state-of-the-art model-free and model-based control strategies. The objective is to evaluate and contrast the performance of these controllers across a wide range of driving scenarios, reflecting the diverse needs of autonomous vehicles. To facilitate the comparative analysis, a comprehensive set of performance metrics is selected, encompassing accuracy, robustness, and comfort. The contributions of this research include the design of a systematic tuning methodology, the use of two novel metrics for stability and comfort comparisons and the evaluation through extensive simulations and real tests in an experimental instrumented vehicle over a wide range of trajectories.

One of the challenges of autonomous driving is to increase the number of situations in which an intelligent vehicle can continue to operate without human intervention. This requires path-tracking control to keep the vehicle stable while following the road, regardless of the shape of the road or the longitudinal speed at which it is moving. In this work, a control strategy framed in the Model-Free Control paradigm is presented to control the lateral vehicle dynamics in a decoupled control architecture. This strategy is designed to guide the vehicle through trajectories with diverse dynamic constraints and over a wide speed range. A design method for this control strategy is proposed, and metrics for trajectory tracking quality, system stability, and passenger comfort are applied to evaluate the controller's performance. Finally, simulation and real-world tests show that the developed strategy is able to track realistic trajectories with a high degree of accuracy, safety, and comfort.

LiDAR-based frameworks combining dynamic occupancy grids and object-level tracking are a popular approach for perception of the environment in autonomous driving applications. This paper presents a novel backchannel from the object-level module to the grid-level module that procures the enhancement of overall performance. This feedback leads to an enhanced grid representation by the inclusion of two new steps that allow semantic classification of the occupied space and the improvement of the dynamic estimation. To this end, objects extracted from the grid are analyzed with respect to potential object classes and displacement. Class likelihoods are filtered over time at cell-level using particles and a naive Bayesian classifier. The displacement information is computed taking into account semantic information and comparing objects in consecutive frames. Then, it is used to obtain velocity measurements that are used to enhance grid's dynamic estimation. In contrast to other approaches in the literature seeking similar objectives, this proposal does not rely on additional sensing technologies or neural networks. The evaluation is conducted with real sensor data in challenging urban scenarios.

Before their massive deployment, autonomous vehicles need to prove in complex scenarios such that they can reach human driving proficiency while guaranteeing higher safety levels. One of the most important human traits to negotiating traffic is the ability to predict the future behavior of surrounding vehicles as a basis for agile and safe navigation. This capability is particularly challenging for an autonomous system in highly interactive driving situations, such as intersections or roundabouts. In this paper, a set of techniques to bring a computationally expensive state-of-the-art motion prediction algorithm to real-time execution are presented with the goal of meeting a standard motion-planning algorithm execution frequency of 5 Hz, which is the primary consumer of motion predictions. This is achieved by applying novel and existing parallelization algorithms that take advantage of graphic processing units (GPUs) through the compute unified device architecture (CUDA) programming language and managing to produce an average 5× speedup over raw C++ in the cases studied. The optimizations are then evaluated in public datasets and a real vehicle on a test track

Computing Occupancy grids with LiDAR data, is a popular strategy for environment representation. In the last two decades, several authors have proposed different methods to render the sensed information into the grids, seeking to obtain computational efficiency or accurate environment modeling. However, no comparison regarding their performance under object detection in autonomous driving applications has been found in the literature. As a result, this work compares six representative LiDAR scan rendering strategies in a quantitative manner. To that end, a novel quantitative evaluation framework for occupancy grids is proposed. It addresses the two main steps of object detection: object segmentation and features estimation, proposing a meaningful procedure, repeatable with other OG approaches.

Model-Free Control has proven its performance in a wide variety of systems. Although its adequate tuning can be achieved using the knowledge of the system and optimization-based approaches, there is not yet a systematic design procedure for this kind of control scheme. In this paper, a non-iterative Three Term Controller tuning procedure is adapted and extended to fit Model-free controllers’ structure. This procedure is successfully applied to design the lateral control of an automated car with realistic performance requirements

Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to assure safety while navigating through highly interactive complex scenarios. In this work, the framework IAMP (Interaction-Aware Motion Prediction), producing multi-modal probabilistic outputs from the integration of a Dynamic Bayesian Network and Markov Chains, is extended with a learning-based approach. The integration of a machine learning model tackles the limitations of the ruled-based mechanism since it can better adapt to different driving styles and driving situations. The method here introduced generates context-dependent acceleration distributions used in a Markov-chain-based motion prediction. This hybrid approach results in better evaluation metrics when compared with the baseline in the four highly-interactive scenarios obtained from publicly available datasets.

Autonomous vehicle technologies have evolved quickly over the last few years, with safety being one of the key requirements for their full deployment. However, ensuring their safety while navigating through highly interactive and complex scenarios remains a critical challenge. To tackle this problem, intention estimation and motion prediction are fundamental. In this work, a method to infer the intentions, based on a Dynamic Bayesian Network (DBN), and predict the motion, using Markov Chains, of the nearby vehicles at unsignalized intersections is proposed. This approach considers all possible corridors of the surrounding traffic participants and takes into account their interactions to infer the probabilities of stopping or crossing the intersection, as well as the probability of being in each of the possible navigable corridors. To achieve this, the DBN is used to model the relationships between the observed states and the unobserved intentions of the nearby agents. The Markov Chain model, obtained from a kinematic model, is used to predict the future motions of the vehicles, taking into account their current state, their inferred intentions, and the uncertainty associated with the prediction. The resulting multi-modal motion predictions are sent to the ego vehicle to navigate through the scene. The proposed method is evaluated in 6 real situations extracted from publicly available datasets and is compared with a model-based and a learn-based baseline models. The results showed that the proposed method outperformed both baselines in terms of accuracy considering the metrics ADE and FDE.

The capabilities of automated vehicles have increased over the last years, and different driving strategies have shown promising results on a variety of scenarios. However, there are still many challenges to be solved, and handling crowded roundabouts is one of them. This kind of scenario requires both safe and efficient maneuvers from the autonomous driving systems in order to maintain a proper traffic flow. This work presents a strategy to generate different speed profiles for a set of path candidates in order to obtain a merging maneuver according to current traffic scene. The proposed mechanism relies on the use of fictitious accelerations generated by leader and lag vehicles, incorporating by design comfort and safety bounds. The autonomous driving system proposed in this work was tested on realistic driving scenarios collected from public datasets and its performance was compared to human drivers on the same scenarios. The results showed in a variety of situations that the automated vehicle was capable of merging into roundabouts with tight merging gaps while maintaining both comfort and safety constraints.

Motion planning is a process of constant negotiation with the rest of the traffic agents and is highly conditioned by their movement prediction. Indeed, an incorrect prediction could cause the motion planning algorithm to adopt overly conservative or reckless behaviors that can eventually become a dangerous driving situation. This paper presents a framework integrating motion planning and interaction-aware motion prediction algo-rithms, which interact with each other and are able to run in real-time on complex areas such as roundabouts or intersections. The proposed motion prediction strategy generates a multi-modal probabilistic estimation of the future positions and intentions of the surrounding vehicles by taking into account traffic rules,vehicle interaction, road geometry and the reference trajectory of the ego-vehicle; the resulting predictions are fed into a sampling-based maneuver and trajectory planning algorithm that identifies the possible collision points for every generated trajectory candi-date and acts accordingly. This framework enables the automated driving system to have a more agile behavior than other strategies that use more simplistic motion prediction models and where the planning stage does not provide feedback. The approach has been successfully evaluated and compared with a state-of-art approach in highly-interactive scenarios generated from public datasets and real-world situations in a software-in-the-loop simulation system.

In order to increase the number of situations in which an intelligent vehicle can operate without human intervention, lateral control is required to accurately guide it in a reference trajectory regardless of the shape of the road or the longitudinal speed. Some studies address this problem by tuning a controller for low and high speeds and including an output adaptation law. In this paper, a strategy framed in the Model-Free Control paradigm is presented to laterally control the vehicle over a wide speed range. Tracking quality, system stability and passenger comfort are thoroughly analyzed and compared to similar control structures. The results obtained both in simulation and with a real vehicle show that the developed strategy tracks a large number of trajectories with high degree of accuracy, safety and comfort.

Dynamic occupancy grids (DOGs) have raised interest in the last years due to their ability to fuse information without explicit data association, to represent free space and arbitrary-shape objects and to estimate obstacles’ dynamics. Different works have presented strategies with demonstrated good performance. Most of them rely on LiDAR sensors, and some have shown that including additional velocity measurements enhance the estimation. This work aims at showing that velocity information can be directly inferred from objects displacement. Thus, a strategy using velocity feedback and its inclusion in the DOG is presented. The qualitative and quantitative analysis of results obtained from real data experimentation show a very good performance, specially in dynamic changing situations.

The behavior of traffic participants is full of uncertainties in the real world. It depends on their intentions, the road layout, and the interaction between them. Probabilistic intention and motion predictions are unavoidable to safely navigate in complex scenarios. In this work, we propose a framework to compute the motion prediction of the surrounding vehicles taking into account all possible routes obtained from a given map. To that end, a Dynamic Bayesian Network is used to model the problem and a particle filter is applied to infer the probability of being on a specific route and the intention to change lanes. Our framework, based on Markov chains, is generic and can handle various road layouts and any number of vehicles. The framework is evaluated in two scenarios: a two-lane highway and a three-lane merging highway. Finally, the influence of a set of lane-changing methods is evaluated on the predictions of the vehicles present on the scene.

Both path and speed planning play key roles in automated driving, specially when a certain comfort level is required. This paper proposes a human-like speed planning method for already defined paths while minimizing travel time. The proposed method is able to compute a time-optimal speed profile that meet the given constrains with regard to speed, acceleration and jerk. For this purpose, an initial accelerationlimited approach is introduced. This algorithm serves as a starting point for the subsequent jerk-limited speed planning. Moreover, fallback strategies are included to manage critical driving situations where initial or final conditions cannot be met. The proposed approach has been tested and validated in an experimental platform through extensive trials in real environments. Its performance has been evaluated both in terms of quality of the computed speed profiles and with respect the required computing time.

This work presents a maneuver planner for automated vehicles, seamlessly integrated with a motion planner, that is able to make tactical decisions to safely navigate in urban environments. The proposed maneuver planner is able to select the most suitable target lane for the ego-vehicle and to manage different regulatory signals like right of way, must stop or pedestrian crossings. The integration with the motion planner allows to select the current maneuver after exploring a reachable set of trajectories, which brings flexibility to the system in complex and dynamic driving scenarios. The architecture was validated on a real vehicle in two urban scenarios with other traffic agents: an intersection with a pedestrian crossing and an overtaking scenario on a two-way road.

Most advanced autonomous driving systems (ADS) today rely on the prior creation of high-definition maps (HD maps). This process is expensive and needs to be performed frequently to keep up with the changing conditions of the road environment. Creating accurate navigation maps online is an alternative to reduce the cost and broaden the current operational design domains (ODD) of modern ADS. This paper offers a snapshot of the state of the art in drivable area estimation, which is an essential technology to deploy ADS in ODDs where HD maps are limited or unavailable. The proposed review introduces a novel architecture breakdown that fits learning-based and non-learning-based techniques and allows the analysis of a set of impactful and recent drivable area algorithms. In addition to that, complimentary information for practitioners is provided: (i) an assessment of the influence of modern sensing technologies on the task under study and (ii) a selection of relevant datasets for evaluation and benchmarking purposes.