KAT‐5: Robust systems for autonomous vehicle navigation in challenging and unknown terrain

Trepagnier, Paul G.; Nagel, Jorge; Kinney, Powell M.; Koutsougeras, Cris; Dooner, Matthew

doi:10.1002/rob.20128

Cited by 28 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This challenge was targeted exactly at the type of problem that our approach intends to address. Although the race did not have any obstacles enroute, only five out of twenty vehicles finished the race (Thrun et al 2006;Urmson et al 2006;Trepagnier et al 2006;Braid et al 2006) providing a testament to the difficulty of following a well-specified outdoor route. Notably, the vehicles that did succeed were equipped with many sensors (in some cases 8-10 laser scanners) to perceive the environment, and in most cases a large amount of computing.…”

Section: Related Workmentioning

confidence: 98%

An efficient system for combined route traversal and collision avoidance

et al. 2008

View full text Add to dashboard Cite

Here we consider the problem of a robot that must follow a previously designated path outdoors. While the nominal path, a series of closely spaced via points, is provided with an assurance that it will lead to the destination, we can't be guaranteed that it will be obstacle free. We present an efficient system capable of both following the path as well as being perceptive and agile enough to avoid obstacles in its way. We present a system that detects obstacles using laser ranging, as well as a layered system that continuously tracks the path, avoiding obstacles and replanning the route when necessary. The distinction of this system is that compared to the state of the art, it is minimal in sensing and computation while achieving high speeds. In this paper, we present an algorithm that is based on models of obstacle avoidance by humans and show variations of the model to deal with practical considerations. We show how the parameters of this model are automatically learned from observation of human operation and discuss limitations of the model. We then show how these models can be extended by adding online route planning and a formulation that allows for operation at varying speeds. We present experimental results from an autonomous vehicle that has operated several hundred kilometers to validate the methodology.

show abstract

Section: Related Workmentioning

confidence: 98%

An efficient system for combined route traversal and collision avoidance

et al. 2008

View full text Add to dashboard Cite

show abstract

“…Testing "early and often" was a strong recommendation of successful participants in the 2005 Grand Challenge (Thrun et al, 2006;Trepagnier, Nagel, Kinney, Koutsourgeras, & Dooner, 2006;Urmson et al, 2006). As newcomers to the Grand Challenge, it was imperative for our team to obtain an autonomous vehicle as quickly as possible.…”

Section: Infrastructure Designmentioning

confidence: 99%

A perception‐driven autonomous urban vehicle

Leonard

How

Teller

et al. 2008

Journal of Field Robotics

407

180

View full text Add to dashboard Cite

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 kinodynamic 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 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 global positioning system-denied and highly dynamic environments with poor a priori information. C 2008 Wiley Periodicals, Inc.

show abstract

“…The problem of autonomous navigation has been well studied in recent decades. Autonomous vehicles, such as Stanley [4], Sandstorm [5], KAT-5 [6] etc. in DARPA Grand Challenge (DGC) 2005 and AMOR [7], MuCAR-3 [8], etc.…”

Section: Introductionmentioning

confidence: 99%

A Polar Rover for Large-Scale Scientific Surveys: Design, Implementation and Field Test Results

Chen

et al. 2015

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Exploration of polar regions is of great importance to scientific research. Unfortunately, due to the harsh environment, most of the regions on the Antarctic continent are still unreachable for humankind. Therefore, in 2011, the Chinese National Antarctic Research Expedition (CHI-NARE) launched a project to design a rover to conduct large-scale scientific surveys on the Antarctic. The main challenges for the rover are twofold: one is the mobility, i.e., how to make a rover that could survive the harsh environment and safely move on the uneven, icy and snowy terrain; the other is the autonomy, in that the robot should be able to move at a relatively high speed with little or no human intervention so that it can explore a large region in a limit time interval under the communication constraints. In this paper, the corresponding techniques, especially the polar rover's design and autonomous navigation algorithms, are introduced in detail. Subsequently, an experimental report of the fields tests on the Antarctic is given to show some preliminary evaluation of the rover. Finally, experiences and existing challenging problems are summarized.

show abstract

KAT‐5: Robust systems for autonomous vehicle navigation in challenging and unknown terrain

Cited by 28 publications

References 11 publications

An efficient system for combined route traversal and collision avoidance

An efficient system for combined route traversal and collision avoidance

A perception‐driven autonomous urban vehicle

A Polar Rover for Large-Scale Scientific Surveys: Design, Implementation and Field Test Results

Contact Info

Product

Resources

About