Fig 2 - uploaded by Sebastian Maierhofer
Content may be subject to copyright.
Source publication
Ensuring the safety of autonomous vehicles is a
challenging task, especially if the planned trajectories do not
consider all traffic rules or they are physically infeasible. Since
replanning the complete trajectory is often computationally
expensive, efficient methods are necessary for resolving such
situations. One solution is to deform or repair...
Contexts in source publication
Context 1
... kinematic single-track model [31] is used since it captures the relevant vehicle dynamics (cf. Fig. 2). The five-dimensional state vector x = [s x , s y , δ, v, Ψ] T consists of the two-dimensional position at the center of the rear axle [s x , s y ] T , the steering angle δ, the longitudinal velocity v, and the orientation Ψ. The control input vector u = [v δ , a long ] T contains the steering velocity v δ and the longitudinal ...
Context 2
... L f w is the forward drive look-ahead distance and η is the heading of the look-ahead points on the target line from the rear axle based on the vehicle orientation (cf. Fig. 2). Different from the original CL-RRT, we use the steering velocity instead of the steering angle as the lateral input to avoid jerky motions. As a result, the steering controller combines the pure-pursuit controller with a PI controller (cf. Fig. 8). The PI controller can be written ...
Similar publications
Based on the theory of planned behavior, this study identifies the causal relationship between attitudinal factors and intention to use transportation mode. A structural equation model was developed based on twelve hypotheses. The main findings and implications of this study are as follows. First, people who want to express themselves through cars...
In the present research paper, the authors provide an extensive overview about a so far uninvestigated approach regarding the research and development (R&D) of Autonomous Vehicle Technologies, an exhaustive investigation concerning the simulation and validation of roundabout situation with radio-controlled (RC) autonomous vehicles, as well as the e...
![Fig. 8. ROS graphic concept [18]](publication/353683869/figure/fig3/AS:1053071517970467@1628083223838/ROS-graphic-concept-18_Q320.jpg)
This paper lays the foundations of an autonomous control system for an electric ATV type vehicle. The conversion of a classic motor vehicle into an electric one is shortly presented and the main advantages deriving from such a motorization especially in terms of the main impact on the environment in the sense that the noxious substances resulting f...
![Fig. 1: Truck Platoon [4]](profile/Sanket-Salvi/publication/357394739/figure/fig1/AS:1154056231895040@1652159855110/Truck-Platoon-4_Q320.jpg)
The past decades have witnessed an increase in the number of electric and non-electric vehicles. Autonomous vehicles are becoming more popular as it was observed that vehicular autonomy could be the possible solution towards increasing road and fuel efficiency. However, due high-cost nature of the solution there is an increasing need for low cost,...
Citations
... Several fallback solutions have been implemented in the area of trajectory planning. In [13], an approach is presented repairing infeasible trajectories. Collision avoidance trajectory planning in [14,15] aims to mitigate a crash or lower its severity when a collision is hardly avoidable. ...
In the realm of autonomous driving, ensuring a secure halt is imperative across diverse scenarios, ranging from routine stops at traffic lights to critical situations involving detected system boundaries of crucial modules. This article presents a novel methodology for swiftly calculating safe stop trajectories. We utilize a clustering method to categorize lane shapes to assign encountered traffic situations at runtime to a set of precomputed resources. Among these resources, there are precalculated halt trajectories along representative lane centers that serve as parametrizations of the optimal control problem. At runtime, the current road settings are identified, and the respective precomputed trajectory is selected and then adjusted to fit the present situation. Here, the perceived lane center is considered a change in the parameters of the optimal control problem. Thus, techniques based on parametric sensitivity analysis can be employed, such as the low-cost feasibility correction. This approach covers a substantial number of lane shapes and exhibits a similar solution quality as a re-optimization to generate a trajectory while demanding only a fraction of the computation time.
... As a result, in Fig. 4e, the ego vehicle is considered legally safe at 2.6s along the intended trajectory but not at 3.8s, as the latter could pose a danger to the pedestrian when it is inattentive and jaywalks. To efficiently ensure safety for the situation at 3.8s, we employ the trajectory repairing method described in [47] and [48]. This approach keeps the trajectory before the TTR unchanged while repairing the remaining part. ...
... However, generating a safe, feasible, and energyefficient trajectory while taking into account full vehicle dynamics in dense traffic is computationally challenging. An informed rapidly-exploring random tree with a closed-loop controller is developed to improve sample efficiency and repair invalid reference trajectories [12]. To realize split-second reactivity to threats, an optimized-based complimentary planner and controller sharing the same interpretation of safety for autonomous driving are proposed [13]. ...
In dense traffic scenarios, ensuring safety while keeping high task performance for autonomous driving is a critical challenge. To address this problem, this paper proposes a computationally-efficient spatiotemporal receding horizon control (ST-RHC) scheme to generate a safe, dynamically feasible, energy-efficient trajectory in control space, where different driving tasks in dense traffic can be achieved with high accuracy and safety in real time. In particular, an embodied spatiotemporal safety barrier module considering proactive interactions is devised to mitigate the effects of inaccuracies resulting from the trajectory prediction of other vehicles. Subsequently, the motion planning and control problem is formulated as a constrained nonlinear optimization problem, which favorably facilitates the effective use of off-the-shelf optimization solvers in conjunction with multiple shooting. The effectiveness of the proposed ST-RHC scheme is demonstrated through comprehensive comparisons with state-of-the-art algorithms on synthetic and real-world traffic datasets under dense traffic, and the attendant outcome of superior performance in terms of accuracy, efficiency and safety is achieved.
... As a result, in Fig. 4e, the ego vehicle is considered legally safe at 2.6s along the intended trajectory but not at 3.8s, as the latter could pose a danger to the pedestrian when it is inattentive and jaywalks. To efficiently ensure safety for the situation at 3.8s, we employ the trajectory repairing method described in [47] and [48]. This approach keeps the trajectory before the TTR unchanged while repairing the remaining part. ...
Scenarios are a crucial element for developing, testing, and verifying autonomous driving systems. However, open-source scenarios are often formulated using different terminologies. This limits their usage across different applications as many scenario representation formats are not directly compatible with each other. To address this problem, we present the first open-source converter from the OpenSCENARIO format to the CommonRoad format, which are two of the most popular scenario formats used in autonomous driving. Our converter employs a simulation tool to execute the dynamic elements defined by OpenSCENARIO. The converter is available at commonroad.in.tum.de and we demonstrate its usefulness by converting publicly available scenarios in the OpenSCENARIO format and evaluating them using CommonRoad tools.
... The latter makes use of only the geometry information of the free space, which can be seen as a path planning problem, and afterward, the time information will be integrated, by indirectly using a simple reference velocity profile. Such a method is called hierarchical trajectory planning as used in, for example, [22]- [26]. Since there are plenty of papers dealing with the path planning problem in the field of robotics, we explore some of the relevant papers regarding this. ...
Collision avoidance is one of the tasks that recently plays an important role in autonomous driving and proves to be challenging. The research normally focuses on object detection, planning, control, or scene modeling. This paper proposes a new method for determining collision-free trajectories in a combination of other aspects listed. It uses the L-shaped fitting algorithm to detect rectangular neighboring obstacles. The Hybrid A* algorithm is combined with Weighted A* to accelerate the planning process and how much the time consumption is improved is investigated. PID and Stanley controllers are coupled to keep the ego vehicle drive according to its references. A realistic interaction of dynamic obstacles, namely vehicles, is also implemented. The entire approach is evaluated using different weights and tested in simulation for unstructured and semi-structured environments using MATLAB. In the end, a real-time capability of 1 s is guaranteed while collision-free trajectories are generated.
... For example, criticality measures are used to validate the safety of autonomous vehicles through various methods, including generating safety-critical scenarios [7]- [11], falsifying the system under test [12], and formally verifying system properties [1]. For motion planning applications, criticality measures help to find traffic conflicts, repair unsafe trajectories, and provide fail-safe solutions [13]- [15]. Model-based and data-driven methods are frequently used to estimate the criticality of a traffic situation [2], [3]. ...
... A more accurate alternative is to compute the TTC with an intended trajectory of the ego vehicle and the given prediction of other vehicles [13], [33], which we call TTC * . Given a most-likely or set-based prediction [59] of a vehicle b, we define that the intended trajectory of the ego vehicle can be executed without collisions through the predicate ...
Criticality measures are essential for autonomous vehicles to capture the complexity of the surrounding environment, trigger emergency maneuvers, and verify safety. However, there is currently no publicly available toolbox that allows researchers to use or evaluate a large number of criticality measures on arbitrary traffic scenarios. To address this issue, we present CommonRoad-CriMe, an open-source toolbox for measuring the criticality of autonomous vehicles in a unified framework. Our toolbox covers a wide range of state-of-the-art criticality measures and provides visualized information to facilitate debugging and showcasing. Numerical experiments demonstrate how our toolbox facilitates the comparison of different criticality measures and the analysis of traffic conflicts. Our toolbox is available at commonroad.in.tum.de.
... [20] and [21] survey the application of various motion planning techniques for autonomous vehicles, providing insight into the use of SBMP for driving in urban environments and highways, respectively. [22] proposes a method for repairing existing trajectories, where infeasible parts of the nominal trajectory are repaired to compute feasible deviations. [23] discretizes the nominal trajectory and places guide points in locations that are infeasible with the nominal, and thereby biases the sampling. ...
This paper addresses local path re-planning for $n$-dimensional systems by introducing an informed sampling scheme and cost function to achieve collision avoidance with minimum deviation from an (optimal) nominal path. The proposed informed subset consists of the union of ellipsoids along the specified nominal path, such that the subset efficiently encapsulates all points along the nominal path. The cost function penalizes large deviations from the nominal path, thereby ensuring current safety in the face of potential collisions while retaining most of the overall efficiency of the nominal path. The proposed method is demonstrated on scenarios related to the navigation of autonomous marine crafts.
... Replanning a complete trajectory, however, is often unnecessary and time-consuming. One interesting approach is trajectory repairing, as visualized in Fig. 1 and proposed in our previous work [3], to overcome this challenge. The concept in [3] only considers scenarios with collisions but does not repair trajectories violating traffic rules formalized in temporal logic, which is addressed in this study. ...
... One interesting approach is trajectory repairing, as visualized in Fig. 1 and proposed in our previous work [3], to overcome this challenge. The concept in [3] only considers scenarios with collisions but does not repair trajectories violating traffic rules formalized in temporal logic, which is addressed in this study. ...
... 1) Time-To-Comply Search: Calculating the TC for establishing the cut-off state is challenging since all possible maneuvers must be evaluated. Similar to the calculation of time-to-react in [3], we underapproximate the TC (cf. Fig. 2) by using a point-mass vehicle model [34] and focusing only on the predicates contained in φ r . ...
Autonomous vehicles must comply with traffic rules. However, most motion planners do not explicitly consider all relevant traffic rules. Once traffic rule violations of an initially-planned trajectory are detected, there is often not enough time to replan the entire trajectory. To solve this problem , we propose to repair the initial trajectory by investigating the satisfiability modulo theories paradigm. This framework makes it efficient to reason whether and how the trajectory can be repaired and, at the same time, determine the part along the trajectory that can remain unchanged. Moreover, the robustness of traffic rule satisfaction is used to formulate a convex optimization problem for generating rule-compliant trajectories. We compare our approach with trajectory replan-ning and demonstrate its usefulness with traffic scenarios from the CommonRoad benchmark suite and recorded data. The evaluation result shows that rule-compliant trajectory repairing is computationally efficient and widely applicable.
Adaptation to changing dynamic situations is yet an open problem for automated driving systems that require robust and efficient solutions. Particularly in the context of motion planning algorithms, this problem is typically addressed by re-planning the whole trajectory or repairing the invalid part. The main drawback of all the current approaches is the increased demand for computational resources, a critical safety issue in automated vehicles. Motivated by this, in this paper we propose a novel and efficient method for trajectory repairing utilizing Bernstein basis polynomials and path-speed decoupling. A robustness metric is introduced to tune the driving behavior. Accurate numerical simulations indicate performance figures typically better than 25ms for a feasible solution in representative driving scenarios, which was not achievable in other state-of-the-art approaches.
