Safe Planning for Self-Driving Via Adaptive Constrained ILQR

Pan, Yanjun; Qi, Lin; Shah, Het; Dolan, John M.

doi:10.1109/iros45743.2020.9340886

Cited by 14 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to further improve the robustness, reference [34] used a probabilistic map represented as Gaussian distribution over remittance values instead of the previous ground map represented as fixed infrared remittance values. It enables the stationary objects and consistent angular reflectivity in the map to be quickly ~0.5 [23], [24] Localisation Expected millisecondlevel [3] Judgement Planning and decision making ~0.1-0.2 [25], [26] Reaction Execution ~0.1 [27], [28] identified by Bayesian inference. Then they used offline SLAM to align the overlapping trajectories in previous sequential map, which makes the localisation system keep learning and improving maps.…”

Section: A Lidar-based Localisationmentioning

confidence: 99%

Real-Time Performance-Focused Localization Techniques for Autonomous Vehicle: A Review

Lü

Smart

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Real-time, accurate, and robust localisation is critical for autonomous vehicles (AVs) to achieve safe, efficient driving, whilst real-time performance is essential for AVs to achieve their current position in time for decision making. To date, no review paper has quantitatively compared the real-time performance between different localisation techniques based on various hardware platforms and programming languages and analysed the relations among localisation methodologies, real-time performance and accuracy. Therefore, this paper discusses the state-of-the-art localisation techniques and analyses their overall performance in AV application. For further analysis, this paper firstly proposes a localisation algorithm operations capability (LAOC)-based equivalent comparison method to compare the relative computational complexity of different localisation techniques; then, it comprehensively discusses the relations among methodologies, computational complexity, and accuracy. Analysis results show that the computational complexity of localisation approaches differs by a maximum of about times, whilst accuracy varies by about 100 times. Vision-and data fusion-based localisation techniques have about 2-5 times potential for improving accuracy compared with lidar-based localisation. Lidar-and vision-based localisation can reduce computational complexity by improving image registration method efficiency. Data fusion-based localisation can achieve better real-time performance compared with lidar-and vision-based localisation because each standalone sensor does not need to develop a complex algorithm to achieve its best localisation potential. Vehicle-toeverything (V2X) technology can improve positioning robustness. Finally, the potential solutions and future orientations of AVs' localisation based on the quantitative comparison results are discussed.

show abstract

Section: A Lidar-based Localisationmentioning

confidence: 99%

Real-Time Performance-Focused Localization Techniques for Autonomous Vehicle: A Review

Lü

Smart

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…This reward should be inversely proportional to the time of crossing the intersection, the total acceleration and speed deviation from the curvature, and the initial speed based on the law of the path following, taking into account the limited possible acceleration and avoidance of collisions. There are several path planning methods, the most promising are LQR [23], ILQR [24], as well as algorithms based on inference rules. Such algorithms should be based on the rules of the road.…”

Section: Parametrized Functional Model Of the Control Systemmentioning

confidence: 99%

Functional Model of a Self-Driving Car Control System

et al. 2021

View full text Add to dashboard Cite

The article describes a structural and functional model of a self-driving car control system, which generates a wide class of mathematical problems. Currently, control systems for self-driving cars are considered at several levels of abstraction and implementation: Mechanics, electronics, perception, scene recognition, control, security, integration of all subsystems into a solid system. Modern research often considers particular problems to be solved for each of the levels separately. In this paper, a parameterized model of the integration of individual components into a complex control system for a self-driving car is considered. Such a model simplifies the design and development of self-driving control systems with configurable automation tools, taking into account the specifics of the solving problem. The parameterized model can be used for CAD design in the field of self-driving car development. A full cycle of development of a control system for a self-driving truck was implemented, which was rub in the “Robocross 2021” competition. The software solution was tested on more than 40 launches of a self-driving truck. Parameterization made it possible to speed up the development of the control system, expressed in man-hours, by 1.5 times compared to the experience of the authors of the article who participated in the same competition in 2018 and 2019. The proposed parameterization was used in the development of individual CAD elements described in this article. Additionally, the implementation of specific modules and functions is a field for experimental research.

show abstract

“…Pek et al [18] used the set-based prediction tool SPOT [19] to predict occupancy of all traffic participants and computed fail-safe trajectories using convex optimization. However, in our previous work [1], we have shown that computing reachable sets of dynamic obstacles over the entire planning horizon leads to an over-conservative planner for general scenarios (i.e., cases other than an emergency requiring a failsafe plan). Instead, we used a two-stage prediction consisting of the short-term and long-term.…”

Section: Related Workmentioning

confidence: 99%

“…Prediction of moving obstacles is achieved using the shortterm and long-term prediction model from [1]. It proposes a combination of a safety-oriented short-term planner and an efficiency-oriented long-term planner.…”

Section: A Dynamic Obstacles Predictionmentioning

confidence: 99%

“…The first research problem arises from the highly uncertain trajectories of surrounding vehicles due to sensing, localization, maneuver or intention uncertainties, etc. Our previous work proposed a two-stage prediction model [1]: the cooperative short-term predictor uses non-linear reachability analysis to provide a safe enclosure of all possible trajectories of dynamic obstacles; while the efficiency-oriented long-term predictor takes a long-term goal into account and avoids over-conservative planning. We have demonstrated its effectiveness of trajectory optimization using constrained ILQR (CILQR) in a Cartesian frame.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Safe planning and control under uncertainty for self-driving

Khaitan¹,

Qi²,

Dolan³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Motion Planning under uncertainty is critical for safe self-driving. In this paper, we propose a unified obstacle avoidance framework that deals with 1) uncertainty in egovehicle motion; and 2) prediction uncertainty of dynamic obstacles from environment. A two-stage traffic participant trajectory predictor comprising short-term and long-term prediction is used in the planning layer to generate safe but not over-conservative trajectories for the ego vehicle. The prediction module cooperates well with existing planning approaches. Our work showcases its effectiveness in a Frenet frame planner. A robust controller using tube MPC guarantees safe execution of the trajectory in the presence of state noise and dynamic model uncertainty. A Gaussian process regression model is used for online identification of the uncertainty's bound. We demonstrate effectiveness, safety, and real-time performance of our framework in the CARLA simulator.

show abstract

Safe Planning for Self-Driving Via Adaptive Constrained ILQR

Cited by 14 publications

References 16 publications

Real-Time Performance-Focused Localization Techniques for Autonomous Vehicle: A Review

Real-Time Performance-Focused Localization Techniques for Autonomous Vehicle: A Review

Functional Model of a Self-Driving Car Control System

Safe planning and control under uncertainty for self-driving

Contact Info

Product

Resources

About