Boss is an autonomous vehicle that uses on-board sensors (global positioning system, lasers, radars, and cameras) to track other vehicles, detect static obstacles, and localize itself relative to a road model. A three-layer planning system combines mission, behavioral, and motion planning to drive in urban environments. The mission planning layer considers which street to take to achieve a mission goal. The behavioral layer determines when to change lanes and precedence at intersections and performs error recovery maneuvers. The motion planning layer selects actions to avoid obstacles while making progress toward local goals. The system was developed from the ground up to address the requirements of the DARPA Urban Challenge using a spiral system development process with a heavy emphasis on regular, regressive system testing. During the National Qualification Event and the 85-km Urban Challenge Final Event, Boss demonstrated some of its capabilities, qualifying first and winning the challenge. C 2008 Wiley Periodicals, Inc.
Boss is an autonomous vehicle that uses on-board sensors (global positioning system, lasers, radars, and cameras) to track other vehicles, detect static obstacles, and localize itself relative to a road model. A three-layer planning system combines mission, behavioral, and motion planning to drive in urban environments. The mission planning layer considers which street to take to achieve a mission goal. The behavioral layer determines when to change lanes and precedence at intersections and performs error recovery maneuvers. The motion planning layer selects actions to avoid obstacles while making progress toward local goals. The system was developed from the ground up to address the requirements of the DARPA Urban Challenge using a spiral system development process with a heavy emphasis on regular, regressive system testing. During the National Qualification Event and the 85-km Urban Challenge Final Event, Boss demonstrated some of its capabilities, qualifying first and winning the challenge. C 2008 Wiley Periodicals, Inc.
This article presents a robust approach to navigating at high speed across desert terrain. A central theme of this approach is the combination of simple ideas and components to build a capable and robust system. A pair of robots were developed, which completed a 212 km Grand Challenge desert race in approximately 7 h. A pathcentric navigation system uses a combination of LIDAR and RADAR based perception sensors to traverse trails and avoid obstacles at speeds up to 15 m/s. The onboard navigation system leverages a human-based preplanning system to improve reliability and robustness. The robots have been extensively tested, traversing over 3500 km of desert trails prior to completing the challenge. This article describes the mechanisms, algorithms, and testing methods used to achieve this performance.
T he effects of Moore's law are apparent everywhere: Chip density, processor speed, memory cost, disk capacity, and network bandwidth are improving relentlessly. As computing costs plummet, a resource that we have ignored until now becomes the limiting factor in computer systems-user attention, namely a person's ability to focus on his or her primary task.Distractions occur especially in mobile environments, because walking, driving, or other real-world interactions often preoccupy the user. A pervasivecomputing environment that minimizes distraction must be context aware, and a pervasive-computing system must know the user's state to accommodate his or her needs.Context-aware applications provide at least two fundamental services: spatial awareness and temporal awareness. Spatially aware applications consider a user's relative and absolute position and orientation. Temporally aware applications consider the time schedules of public and private events. With an interdisciplinary class of Carnegie Mellon University (CMU) students, we developed and implemented a context-aware, pervasive-computing environment that minimizes distraction and facilitates collaborative design. Our approachTo identify the types of distraction that occur during the design process, we created an activity-attention matrix-the Distraction Matrix (see Figure 1). The Distraction Matrix categorizes activities as information (active and passive), communication (artificial, formal, and informal), and creation (contribution). Subcategories specify the types of primary activity within each category. For example, receiving information is a type of active-information activity, and initiating communication is a type of artificialcommunication activity.We based each distraction's location on how long it interrupts a primary activity. We categorized interruption durations as snap, pause, tangent, and extended. A snap distraction is one you usually complete in a few seconds, such as checking your watch; it should not interrupt your primary activity. A pause distraction involves stopping the primary activity, switching to a related one, and then switching back within a few minutes. Pulling over to the side of the road and checking directions is an example. A tangent distraction, such as receiving an unrelated phone call, is of medium duration and is unrelated to your primary activity. An extended distraction, such as stopping at a motel and resting for the night, is a relatively long-term interruption of your primary activity. ApplicationsWe equipped the campus with 400 wireless-networking access points, enabling wireless coverage for the entire campus. To move distractions toward the Distraction Matrix's left (snap) side, we implemented a complementary set of interactive applications and services that support mobile team-design activities. (See the related sidebar for information on relevant work in context-aware computing.) Portable Help Desk. Because they have many meetings at various times and locations, students are often To minimize distractions, a p...
This article presents a robust approach to navigating at high speed across desert terrain. A central theme of this approach is the combination of simple ideas and components to build a capable and robust system. A pair of robots were developed, which completed a 212 km Grand Challenge desert race in approximately 7 h. A pathcentric navigation system uses a combination of LIDAR and RADAR based perception sensors to traverse trails and avoid obstacles at speeds up to 15 m/s. The onboard navigation system leverages a
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.