A Perception-Driven Autonomous Urban Vehicle

DOI: 10.1007/978-3-642-03991-1_5 In book: The DARPA Urban Challenge, pp.163-230


This paper describes the architecture and implementation of an autonomous passenger vehicle designed to navigate using locally
perceived information in preference to potentially inaccurate or incomplete map data. The vehicle architecture was designed
to handle the original DARPA Urban Challenge requirements of perceiving and navigating a road network with segments defined
by sparse waypoints. The vehicle implementation includes many heterogeneous sensors with significant communications and computation
bandwidth to capture and process high-resolution, high-rate sensor data. The output of the comprehensive environmental sensing
subsystem is fed into a kino-dynamic motion planning algorithm to generate all vehicle motion. The requirements of driving
in lanes, three-point turns, parking, and maneuvering through obstacle fields are all generated with a unified planner. A
key aspect of the planner is its use of closed-loop simulation in a Rapidly-exploring Randomized Trees (RRT) algorithm, which
can randomly explore the space while efficiently generating smooth trajectories in a dynamic and uncertain environment. The
overall system was realized through the creation of a powerful new suite of software tools for message-passing, logging, and
visualization. These innovations provide a strong platform for future research in autonomous driving in GPS-denied and highly
dynamic environments with poor a priori information.

Download full-text


Available from: Emilio Frazzoli
  • Source
    • "Furthermore , Voronoi diagrams on their own are not suitable for on-road path-planning, since Voronoi edges, along which a vehicle navigates, can potentially be discontinuous and unsuitable for non-holonomic vehicle. Occupancy grids (Kolski et al., 2006; Bohren et al., 2008; Hundelshausen et al., 2008; Kammel et al., 2008; Leonard et al., 2008; Zhao et al., 2011; Li et al., 2013; Xu et al., 2014) and costmaps (Bacha et al., 2008; Rauskolb et al., 2008; Schröder et al., 2008; Himmelsbach et al., 2009; Murphy and Newman, 2011; Broggi et al., 2012) work in a similar way; they both discretise the state space into a grid and each cell of the grid is associated with a probability of the cell being occupied by an obstacle, or a cost proportional to the feasibility or risk of traversal. Risk or feasibility is primarily calculated by considering the presence of obstacles, lane and road boundaries. "
    [Show abstract] [Hide abstract]
    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.
    Full-text · Article · Nov 2015 · Transportation Research Part C Emerging Technologies
  • Source
    • "The state of the art in high-speed 3D sensing for mobile robots is achieved with the Velodyne sensor. This device, in its HDL32 and HDL64 versions, is tailored to scan wide areas at high frame rates, and is commonplace in research in autonomous vehicles (Leonard et al., 2008). The HDL64 device provides point clouds with over 1.3 M points per second on a 360 degree horizontal view of the scene with a limited vertical field of view of 26.8 degrees and up to 120 m (Spinello, Luber, & Arras, 2011). "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents two techniques to detect and classify navigable terrain in complex three-dimensional (3D) environments. The first method is a low level on-line mechanism aimed at detecting obstacles and holes at a fast frame rate using a time-of-flight camera as the main sensor. The second technique is a high-level offline classification mechanism that learns traversable regions from larger 3D point clouds acquired with a laser range scanner. We approach the problem using Gaussian processes as a regression tool, in which the terrain parameters are learned, and also for classification, using samples from traversed areas to build the traversable terrain class. The two methods are compared against unsupervised classification, and sample trajectories are generated in the classified areas using a nonholonomic path planner. We show results of both the low-level and the high-level terrain classification approaches in simulations and in real-time navigation experiments using a Segway RMP400 robot.
    Full-text · Article · Jan 2015 · Journal of Field Robotics
  • Source
    • "DARPA evaluated capabilities in different kinds of environments, urban and rural ones. Several cars were developed for this challenges [2] [3] [4]. This challenge consists of a strong step for algorithms evaluation, where the winner was the car that reaches first its target location. "
    [Show abstract] [Hide abstract]
    ABSTRACT: For decades, scientists have dreamed of building autonomous cars that can drive without a human driver. Progress in this kind of research recently received an increasing attention in car industries. There are many autonomous car models recently developed. However, they are still infancy since they still lack efficiency and reliability. To obtain efficient and reliable systems, the validation process plays an important role. Nowadays, the validation is strongly related to the number of kilometers of drive. Thus, simulation techniques are used before going into real world driving. We focused our work on developing a methodology to smothly move from simulation into real world car driving. We defined a versatile architecture that simplifies the evaluation of different types of algorithms. Several evaluation systems are shown and discussed.
    Full-text · Conference Paper · Jun 2013
Show more