Trajectory planning for vehicle autonomous driving with uncertainties
20 Nov 2014-pp 34-38
TL;DR: In this paper, a novel method on dynamic trajectory planning for intelligent vehicle driving under traffic environment with uncertainties is proposed, where the statistical characteristics of traffic vehicle motion are first analyzed with a traffic vehicle model, in which the inputs are considered to be random variables with certain probability distribution.
Abstract: This paper proposes a novel method on dynamic trajectory planning for intelligent vehicle driving under traffic environment with uncertainties. The statistical characteristics of traffic vehicle motion are first analyzed with a traffic vehicle model, in which the inputs are considered to be random variables with certain probability distribution. Therefore the output of the model can be calculated via unscented transformation for probabilistic spread. Then the overall collision probability of the candidate trajectories is assessed with certain confidence level. Finally a trajectory planning method is employed to achieve multiple objectives for lane change maneuver with combined efficiency and comfort. Simulation is conducted with results demonstrating that the proposed method is valid and effective.
Citations
More filters
Abstract: Currently autonomous or self-driving vehicles are at the heart of academia and industry research because of its multi-faceted advantages that includes improved safety, reduced congestion, lower emissions and greater mobility. Software is the key driving factor underpinning autonomy within which planning algorithms that are responsible for mission-critical decision making hold a significant position. While transporting passengers or goods from a given origin to a given destination, motion planning methods incorporate searching for a path to follow, avoiding obstacles and generating the best trajectory that ensures safety, comfort and efficiency. A range of different planning approaches have been proposed in the literature. The purpose of this paper is to review existing approaches and then compare and contrast different methods employed for the motion planning of autonomous on-road driving that consists of (1) finding a path, (2) searching for the safest manoeuvre and (3) determining the most feasible trajectory. Methods developed by researchers in each of these three levels exhibit varying levels of complexity and performance accuracy. This paper presents a critical evaluation of each of these methods, in terms of their advantages/disadvantages, inherent limitations, feasibility, optimality, handling of obstacles and testing operational environments. Based on a critical review of existing methods, research challenges to address current limitations are identified and future research directions are suggested so as to enhance the performance of planning algorithms at all three levels. Some promising areas of future focus have been identified as the use of vehicular communications (V2V and V2I) and the incorporation of transport engineering aspects in order to improve the look-ahead horizon of current sensing technologies that are essential for planning with the aim of reducing the total cost of driverless vehicles. This critical review on planning techniques presented in this paper, along with the associated discussions on their constraints and limitations, seek to assist researchers in accelerating development in the emerging field of autonomous vehicle research.
599 citations
01 Jun 2018
TL;DR: AutonoVi-Sim is a collection of high-level extensible modules which allows the rapid development and testing of vehicle configurations and facilitates construction of complex traffic scenarios and training of deep-learning algorithms.
Abstract: We present AutonoVi-Sim, a novel high-fidelity simulation platform for autonomous driving data generation and driving strategy testing. AutonoVi-Sim is a collection of high-level extensible modules which allows the rapid development and testing of vehicle configurations and facilitates construction of complex traffic scenarios. Autonovi-Sim supports multiple vehicles with unique steering or acceleration limits, as well as unique tire parameters and dynamics profiles. Engineers can specify the specific vehicle sensor systems and vary time of day and weather conditions to generate robust data and gain insight into how conditions affect the performance of a particular algorithm. In addition, AutonoVi-Sim supports navigation for non-vehicle traffic participants such as cyclists and pedestrians, allowing engineers to specify routes for these actors, or to create scripted scenarios which place the vehicle in dangerous reactive situations. Autonovi-Sim facilitates training of deep-learning algorithms by enabling data export from the vehicle's sensors, including camera data, LIDAR, relative positions of traffic participants, and detection and classification results. Thus, AutonoVi-Sim allows for the rapid prototyping, development and testing of autonomous driving algorithms under varying vehicle, road, traffic, and weather conditions. In this paper, we detail the simulator and provide specific performance and data benchmarks.
56 citations
Cites background from "Trajectory planning for vehicle aut..."
...[28] demonstrate the use of prediction functions and trajectory set generation to plan safe lane-changes....
[...]
24 Mar 2017
TL;DR: AutonoVi as discussed by the authors is based on optimization-based maneuver planning that supports dynamic lane-changes, swerving, and braking in all traffic scenarios and guides the vehicle to its goal position.
Abstract: We present AutonoVi, a novel algorithm for autonomous vehicle navigation that supports dynamic maneuvers and integrates traffic constraints and norms. Our approach is based on optimization-based maneuver planning that supports dynamic lane-changes, swerving, and braking in all traffic scenarios and guides the vehicle to its goal position. We take into account various traffic constraints, including collision avoidance with other vehicles, pedestrians, and cyclists using control velocity obstacles. We use a data-driven approach to model the vehicle dynamics for control and collision avoidance. Furthermore, our trajectory computation algorithm takes into account traffic rules and behaviors, such as stopping at intersections and stoplights, based on an arc-spline representation. We have evaluated our algorithm in a simulated environment and tested its interactive performance in urban and highway driving scenarios with tens of vehicles, pedestrians, and cyclists. These scenarios include jaywalking pedestrians, sudden stops from high speeds, safely passing cyclists, a vehicle suddenly swerving into the roadway, and high-density traffic where the vehicle must change lanes to progress more effectively.
38 citations
TL;DR: In this paper, the authors present an exhaustive and critical review of the existing approaches on motion and behavior planning for AVs in terms of their feasibility, capability in handling dynamic constraints and obstacles, and optimality of motion for comfort.
36 citations
01 Jun 2020
TL;DR: The results show that the simulation produced human-like flexibility when planning trajectories in a multi-interaction environment, and the travel time of AVs did not show a statistically significant difference when compared with manually driven vehicles (MVs).
Abstract: An essential and challenging task for autonomous vehicles (AVs) is turning at mixed-flow intersections when they interact with motorized, non-motorized and pedestrian traffic simultaneously. In these situations, sensor measurement noise and blind zones create additional complexity in an already problematic environment. In order to make motion planning feasible in a multi-interaction environment with detection uncertainty feasible, this article proposes a hierarchical framework that divides the highly-related driving process into a decision, planning and action layer. The decision layer first employs a logit model combined with Bayes’ theorem to make a discrete choice about whether to turn or not. Then, the plan layer initializes a local trajectory with selected waypoints considering the location of interacting objects based on a Bezier curve. Finally, feedback is used to adjust the vehicle's decision and trajectory plan when collision risks increase due to the unexpected behavior of other objects. Additionally, in order to consider sensor data noise and blind zones of AVs, an Extended Kalman filter (EKF) was used to estimate the status of sensory targets. The performance of the proposed model was compared with drivers’ performance for the same turning scenarios at two mixed-flow intersections. The results show that the simulation produced human-like flexibility when planning trajectories in a multi-interaction environment. Moreover, the travel time of AVs did not show a statistically significant difference when compared with manually driven vehicles (MVs). Instead, the AVs actually performed better in terms of safety than the MVs.
27 citations
References
More filters
TL;DR: The objective of this work is to survey and put in perspective the existing IMM methods for target tracking problems, with special attention to the assumptions underlying each algorithm and its applicability to various situations.
Abstract: The Interacting Multiple Model (IMM) estimator is a suboptimal hybrid filter that has been shown to be one of the most cost-effective hybrid state estimation schemes. The main feature of this algorithm is its ability to estimate the state of a dynamic system with several behavior modes which can "switch" from one to another. In particular, the IMM estimator can be a self-adjusting variable-bandwidth filter, which makes it natural for tracking maneuvering targets. The importance of this approach is that it is the best compromise available currently-between complexity and performance: its computational requirements are nearly linear in the size of the problem (number of models) while its performance is almost the same as that of an algorithm with quadratic complexity. The objective of this work is to survey and put in perspective the existing IMM methods for target tracking problems. Special attention is given to the assumptions underlying each algorithm and its applicability to various situations.
1,024 citations
TL;DR: This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation.
Abstract: This paper presents a real-time path planning algorithm that guarantees probabilistic feasibility for autonomous robots with uncertain dynamics operating amidst one or more dynamic obstacles with uncertain motion patterns. Planning safe trajectories under such conditions requires both accurate prediction and proper integration of future obstacle behavior within the planner. Given that available observation data is limited, the motion model must provide generalizable predictions that satisfy dynamic and environmental constraints, a limitation of existing approaches. This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation. Obstacle trajectory GP predictions are conditioned on dynamically feasible paths identified from the reachability analysis, yielding more accurate predictions of future behavior. RR-GP predictions are integrated with a robust path planner, using chance-constrained RRT, to identify probabilistically feasible paths. Theoretical guarantees of probabilistic feasibility are shown for linear systems under Gaussian uncertainty; approximations for nonlinear dynamics and/or non-Gaussian uncertainty are also presented. Simulations demonstrate that, with this planner, an autonomous vehicle can safely navigate a complex environment in real-time while significantly reducing the risk of collisions with dynamic obstacles.
265 citations
TL;DR: This work proposes modeling target motion patterns as a mixture of Gaussian processes with a Dirichlet process prior over mixture weights, which provides an adaptive representation for each individual motion pattern and automatically adjusts the complexity of the motion model based on the available data.
Abstract: The most difficult--and often most essential--aspect of many interception and tracking tasks is constructing motion models of the targets Experts rarely can provide complete information about a target's expected motion pattern, and fitting parameters for complex motion patterns can require large amounts of training data Specifying how to parameterize complex motion patterns is in itself a difficult task
In contrast, Bayesian nonparametric models of target motion are very flexible and generalize well with relatively little training data We propose modeling target motion patterns as a mixture of Gaussian processes (GP) with a Dirichlet process (DP) prior over mixture weights The GP provides an adaptive representation for each individual motion pattern, while the DP prior allows us to represent an unknown number of motion patterns Both automatically adjust the complexity of the motion model based on the available data Our approach outperforms several parametric models on a helicopter-based car-tracking task on data collected from the greater Boston area
158 citations
13 Oct 2013
TL;DR: A two fold optimization-based method is proposed for stationary trajectory planning as well as dynamic trajectory planning in the presence of a dynamic traffic environment to achieve quick and safe reaction to the changing driving environment and optimal balance between vehicle performance and driving comfort.
Abstract: Trajectory planning is one of the key and challenging tasks in autonomous driving. This paper proposes a novel method that dynamically plans trajectories, with the aim to achieve quick and safe reaction to the changing driving environment and optimal balance between vehicle performance and driving comfort. With the proposed method, such complex maneuvers can be decomposed into two sub-maneuvers, i.e., lane change and lane keeping, or their combinations, such that the trajectory planning is generalized and simplified, mainly based on lane change maneuvers. A two fold optimization-based method is proposed for stationary trajectory planning as well as dynamic trajectory planning in the presence of a dynamic traffic environment. Simulation is conducted to demonstrate the efficiency and effectiveness of the proposed method.
70 citations
"Trajectory planning for vehicle aut..." refers background in this paper
...Firstly, based on current states, all possible trajectories of the host vehicle are produced by a vehicle-model-based trajectory generator which has been verified in previous work [5]....
[...]