Results 1 - 10
of
59
Learning to Search: Functional Gradient Techniques for Imitation Learning
- Autonomous Robots
, 2009
"... Programming robot behavior remains a challenging task. While it is often easy to abstractly define or even demonstrate a desired behavior, designing a controller that embodies the same behavior is difficult, time consuming, and ultimately expensive. The machine learning paradigm offers the promise o ..."
Abstract
-
Cited by 60 (19 self)
- Add to MetaCart
(Show Context)
Programming robot behavior remains a challenging task. While it is often easy to abstractly define or even demonstrate a desired behavior, designing a controller that embodies the same behavior is difficult, time consuming, and ultimately expensive. The machine learning paradigm offers the promise of enabling “programming by demonstration ” for developing high-performance robotic systems. Unfortunately, many “behavioral cloning ” (Bain & Sammut, 1995; Pomerleau, 1989; LeCun et al., 2006) approaches that utilize classical tools of supervised learning (e.g. decision trees, neural networks, or support vector machines) do not fit the needs of modern robotic systems. These systems are often built atop sophisticated planning algorithms that efficiently reason far into the future; consequently, ignoring these planning algorithms in lieu of a supervised learning approach often leads to myopic and poor-quality robot performance. While planning algorithms have shown success in many real-world applications ranging from legged locomotion (Chestnutt et al., 2003) to outdoor unstructured navigation (Kelly et al., 2004; Stentz, 2009), such algorithms rely on fully specified cost functions that map sensor readings and environment models to quantifiable costs. Such cost functions are usually manually designed and programmed. Recently, a set of techniques has been developed that explore learning these functions from expert human demonstration.
Path Planning for Autonomous Underwater Vehicles
"... Abstract — Efficient path planning algorithms are a crucial issue for modern autonomous underwater vehicles. Classical path planning algorithms in artificial intelligence are not designed to deal with wide continuous environments prone to currents. We present a novel Fast Marching based approach to ..."
Abstract
-
Cited by 56 (9 self)
- Add to MetaCart
Abstract — Efficient path planning algorithms are a crucial issue for modern autonomous underwater vehicles. Classical path planning algorithms in artificial intelligence are not designed to deal with wide continuous environments prone to currents. We present a novel Fast Marching based approach to address the following issues. First, we develop an algorithm we call FM * to efficiently extract a continuous path from a discrete representation of the environment. Secondly we take underwater currents into account thanks to an anisotropic extension of the original Fast Marching algorithm. Thirdly, the vehicle turning radius is introduced as a constraint on the optimal path curvature for both isotropic and anisotropic medias. Finally, a multiresolution method is introduced to speed up the overall path planning process. Index Terms — path planning, Fast Marching, FM * algorithm, autonomous underwater vehicle, turning radius, currents, multiresolution method. I.
Theta*: Any-angle path planning on grids.
, 2007
"... Abstract Grids with blocked and unblocked cells are often used to represent terrain in computer games and robotics. However, paths formed by grid edges can be sub-optimal and unrealistic looking, since the possible headings are artificially constrained. We present Theta*, a variant of A*, that prop ..."
Abstract
-
Cited by 42 (6 self)
- Add to MetaCart
(Show Context)
Abstract Grids with blocked and unblocked cells are often used to represent terrain in computer games and robotics. However, paths formed by grid edges can be sub-optimal and unrealistic looking, since the possible headings are artificially constrained. We present Theta*, a variant of A*, that propagates information along grid edges without constraining the paths to grid edges. Theta* is simple, fast and finds short and realistic looking paths. We compare Theta* against both Field D*, the only other variant of A* that propagates information along grid edges without constraining the paths to grid edges, and A* with post-smoothed paths. Although neither path planning method is guaranteed to find shortest paths, we show experimentally that Theta* finds shorter and more realistic looking paths than either of these existing techniques.
High Performance Outdoor Navigation from Overhead Data using Imitation Learning
"... Abstract — High performance, long-distance autonomous navigation is a central problem for field robotics. Efficient navigation relies not only upon intelligent onboard systems for perception and planning, but also the effective use of prior maps and knowledge. While the availability and quality of l ..."
Abstract
-
Cited by 20 (13 self)
- Add to MetaCart
(Show Context)
Abstract — High performance, long-distance autonomous navigation is a central problem for field robotics. Efficient navigation relies not only upon intelligent onboard systems for perception and planning, but also the effective use of prior maps and knowledge. While the availability and quality of low cost, high resolution satellite and aerial terrain data continues to rapidly improve, automated interpretation appropriate for robot planning and navigation remains difficult. Recently, a class of machine learning techniques have been developed that rely upon expert human demonstration to develop a function mapping overhead data to traversal cost. These algorithms choose the cost function so that planner behavior mimics an expert’s demonstration as closely as possible. In this work, we extend these methods to automate interpretation of overhead data. We address key challenges, including interpolation-based planners, non-linear approximation techniques, and imperfect expert demonstration, necessary to apply these methods for learning to search for effective terrain interpretations. We validate our approach on a large scale outdoor robot during over 300 kilometers of autonomous traversal through complex natural environments. I.
Overview of the Mars Exploration Rovers Autonomous Mobility and Vision Capabilities
- IEEE International Conference on Robotics and Automation (ICRA
, 2007
"... Abstract — NASA’s Mars Exploration Rovers have set the standard for autonomous robotic exploration of planetary surfaces. Their abilities to detect and avoid geometric hazards, and measure and compensate for slip or heading changes, have made it possible to drive farther and in highly sloped areas, ..."
Abstract
-
Cited by 20 (4 self)
- Add to MetaCart
Abstract — NASA’s Mars Exploration Rovers have set the standard for autonomous robotic exploration of planetary surfaces. Their abilities to detect and avoid geometric hazards, and measure and compensate for slip or heading changes, have made it possible to drive farther and in highly sloped areas, increasing the science return of the mission. Software updates that took place during the more than three year mission have increased their abilities even further, raising the bar for the remainder of their mission and all that will follow. In this paper we summarize the autonomous capabilities available on the Mars Exploration Rovers following the September 2006 software update. 1. BACKGROUND All spacecraft include a high degree of autonomy by necessity. Capabilities included in spacecraft launched from
Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain
, 2010
"... Rough terrain autonomous navigation continues to pose a challenge to the robotics community. Robust navigation by a mobile robot depends not only on the individual performance of perception and planning systems, but on how well these systems are coupled. When traversing complex unstructured terrain, ..."
Abstract
-
Cited by 17 (7 self)
- Add to MetaCart
(Show Context)
Rough terrain autonomous navigation continues to pose a challenge to the robotics community. Robust navigation by a mobile robot depends not only on the individual performance of perception and planning systems, but on how well these systems are coupled. When traversing complex unstructured terrain, this coupling (in the form of a cost function) has a large impact on robot behavior and performance, necessitating a robust design. This paper explores the application of Learning from Demonstration to this task for the Crusher autonomous navigation platform. Using expert examples of desired navigation behavior, mappings from both online and offline perceptual data to planning costs are learned. Challenges in adapting existing techniques to complex online planning systems and imperfect demonstration are addressed, along with additional practical considerations. The benefits to autonomous performance of this approach are examined, as well as the decrease in necessary designer effort. Experimental results are presented from autonomous traverses through complex natural environments. 1
State Space Sampling of Feasible Motions for High Performance Mobile Robot Navigation in Complex Environments
- Journal of Field Robotics
, 2008
"... Sampling in the space of controls or actions is a well-established method for ensuring feasible local motion plans. However, as mobile robots advance in performance and competence in complex environments, this classical motion-planning technique ceases to be effective. When environmental constraints ..."
Abstract
-
Cited by 16 (6 self)
- Add to MetaCart
(Show Context)
Sampling in the space of controls or actions is a well-established method for ensuring feasible local motion plans. However, as mobile robots advance in performance and competence in complex environments, this classical motion-planning technique ceases to be effective. When environmental constraints severely limit the space of acceptable motions or when global motion planning expresses strong preferences, a state space sampling strategy is more effective. Although this has been evident for some time, the practical question is how to achieve it while also satisfying the severe constraints of vehicle dynamic feasibility. The paper presents an effective algorithm for state space sampling utilizing a model-based trajectory generation approach. This method enables high-speed navigation in highly constrained and/or partially known environments such as trails, roadways, and dense off-road obstacle fields. C ○ 2008 Wiley Periodicals, Inc. 1.
Global path planning on board the mars exploration rovers
- In IEEE Aerospace Conference
, 2007
"... Rovers (MERs), Spirit and Opportunity, began searching the surface of Mars for evidence of past water activity. In order to localize and approach scientifically interesting targets, the rovers employ an on-board navigation system. Given the latency in sending commands from Earth to the Martian rover ..."
Abstract
-
Cited by 15 (0 self)
- Add to MetaCart
(Show Context)
Rovers (MERs), Spirit and Opportunity, began searching the surface of Mars for evidence of past water activity. In order to localize and approach scientifically interesting targets, the rovers employ an on-board navigation system. Given the latency in sending commands from Earth to the Martian rovers (and in receiving return data), a high level of navigational autonomy is desirable. Autonomous navigation with hazard avoidance (AutoNav) is currently performed using a local path planner called GESTALT (Grid-based Estimation of Surface Traversability Applied to Local Terrain). GESTALT uses stereo cameras to evaluate terrain safety and avoid obstacles. GESTALT works well to guide the rovers around narrow and isolated hazards, however, it is susceptible to failure when clusters of closely spaced, non-traversable rocks form extended obstacles. In May 2005, a new technology task was
Planning with uncertainty in position using high-resolution maps
, 2008
"... Navigating autonomously is one of the most important problems facing outdoor mobile robots. This task is extremely difficult if no prior information is available and is trivial if perfect prior information is available and the position of the robot is precisely known. Perfect prior maps are rare, bu ..."
Abstract
-
Cited by 14 (2 self)
- Add to MetaCart
Navigating autonomously is one of the most important problems facing outdoor mobile robots. This task is extremely difficult if no prior information is available and is trivial if perfect prior information is available and the position of the robot is precisely known. Perfect prior maps are rare, but good-quality, high-resolution prior maps are increasingly available. Although the position of the robot is usually known through the use of the Global Position System (GPS), there are many scenarios in which GPS is not available, or its reliability is compromised by different types of interference such as mountains, buildings, foliage or jamming. If GPS is not available, the position estimate of the robot depends on dead-reckoning alone, which drifts with time and can accrue very large errors. Most existing approaches to path planning and navigation for outdoor environments are unable to use prior maps if the position of the robot is not precisely known. Often these approaches end up performing the much harder task of navigating without prior information. This thesis addresses the problem of planning paths with uncertainty in position for large outdoor environments. The objective is to be able to reliably navigate autonomously
Laser-based navigation enhanced with 3d time-of-flight data
- In Proce ICRA ’09
, 2009
"... Abstract — Navigation and obstacle avoidance in robotics using planar laser scans has matured over the last decades. They basically enable robots to penetrate highly dynamic and populated spaces, such as people’s home, and move around smoothly. However, in an unconstrained environment the two-dimens ..."
Abstract
-
Cited by 13 (2 self)
- Add to MetaCart
(Show Context)
Abstract — Navigation and obstacle avoidance in robotics using planar laser scans has matured over the last decades. They basically enable robots to penetrate highly dynamic and populated spaces, such as people’s home, and move around smoothly. However, in an unconstrained environment the two-dimensional perceptual space of a fixed mounted laser is not sufficient to ensure safe navigation. In this paper, we present an approach that pools a fast and reliable motion generation approach with modern 3D capturing techniques using a Time-of-Flight camera. Instead of attempting to implement full 3D motion control, which is computationally more expensive and simply not needed for the targeted scenario of a domestic robot, we introduce a “virtual laser”. For the originally solely laser-based motion generation the technique of fusing real laser measurements and 3D point clouds into a continuous data stream is 100 % compatible and transparent. The paper covers the general concept, the necessary extrinsic calibration of two very different types of sensors, and exemplarily illustrates the benefit which is to avoid obstacles not being perceivable in the original laser scan. I.
