A Perception-Driven Autonomous Urban Vehicle

DOI: 10.1007/978-3-642-03991-1_5


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, Oct 06, 2015
28 Reads
  • Source
    • "Recent years have witnessed major advances in designing and building autonomous vehicles to realize safer and more fuel efficient future cars [5] [31] [18]. Past work in this domain [14] [8] [17], including the DARPA Urban Challenge and the Google autonomous car, focuses on issues related to perception, efficient path planning, obstacle detection, etc. In contrast, this paper focuses on designing a communication protocol that is most suitable for sharing sensory data between autonomous vehicles. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper introduces CarSpeak, a communication system for autonomous driving. CarSpeak enables a car to query and access sensory information captured by other cars in a manner similar to how it accesses information from its local sensors. CarSpeak adopts a content-centric approach where information objects -- i.e., regions along the road -- are first class citizens. It names and accesses road regions using a multi-resolution system, which allows it to scale the amount of transmitted data with the available bandwidth. CarSpeak also changes the MAC protocol so that, instead of having nodes contend for the medium, contention is between road regions, and the medium share assigned to any region depends on the number of cars interested in that region. CarSpeak is implemented in a state-of-the-art autonomous driving system and tested on indoor and outdoor hardware testbeds including an autonomous golf car and 10 iRobot Create robots. In comparison with a baseline that directly uses 802.11, CarSpeak reduces the time for navigating around obstacles by 2.4x, and reduces the probability of a collision due to limited visibility by 14x.
    ACM SIGCOMM Computer Communication Review 10/2012; 42(4). DOI:10.1145/2342356.2342403 · 1.12 Impact Factor
  • Source
    • "Vehicle autonomy is considered as an efficient solution to automatically rebalance vehicles among stations with asymmetric resources, and enable a one-way vehicle sharing option in MoD systems. The ability of vehicles to drive autonomously in urban scenarios has matured as evidenced by the results of the DARPA Urban Challenge (DUC) [2]. However, the developed vehicles depend on a variety of sensors, some of which are prohibitively expensive while others are highly specialized, causing the deployment to be economically infeasible. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We present an autonomous vehicle providing mobility-on-demand service in a crowded urban environment. The focus in developing the vehicle has been to attain autonomous driving with minimal sensing and low cost, off-the-shelf sensors to ensure the system's economic viability. The autonomous vehicle has successfully completed over 50 km handling numerous mobility requests during the course of multiple demonstrations. The video provides an overview of our approach, with special comments on our localization and perception modules showcasing one such request being serviced.
    Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on; 01/2012
  • Source
    • "An algorithm that solves this problem is said to be complete, if it returns such a control input when one exists and returns failure otherwise. This problem of navigating through a complex environment is one of the fundamental problems in robotics [7] with applications including, but not limited to, autonomous driving [8], manipulation planing [9], logistics [10], and medical surgery [11]. The motion planning problem also has several applications outside the domain of robotics, ranging from verification to computational biology [12]–[14]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Incremental sampling-based motion planning algorithms such as the Rapidly-exploring Random Trees (RRTs) have been successful in efficiently solving computationally challenging motion planning problems involving complex dynamical systems. A recently proposed algorithm, called the RRT*, also provides asymptotic optimality guarantees, i.e., almost-sure convergence to optimal trajectories (which the RRT algorithm lacked) while maintaining the computational efficiency of the RRT algorithm. In this paper, time-optimal maneuvers for a high-speed off-road vehicle taking tight turns on a loose surface are studied using the RRT* algorithm. Our simulation results show that the aggressive skidding maneuver, usually called the trail-braking maneuver, naturally emerges from the RRT* algorithm as the minimum-time trajectory. Along the way, we extend the RRT* algorithm to handle complex dynamical systems, such as those that are described by nonlinear differential equations and involve high-dimensional state spaces, which may be of independent interest. We also exploit the RRT* as an anytime computation framework for nonlinear optimization problems.
    Decision and Control and European Control Conference (CDC-ECC), 2011 50th IEEE Conference on; 12/2011
Show more