Incremental Learning for Motion Prediction of Pedestrians and Vehicles

Alejandro Dizan Vasquez Govea

ISBN 10: 3642136419 / ISBN 13: 9783642136412

Verlag: Springer Berlin Heidelberg, Springer Berlin Heidelberg Jun 2010, 2010

Beschreibung

Neuware -Roboticsis undergoingamajortransformationinscopeanddimension.From a largelydominantindustrialfocus,roboticsis rapidly expandinginto human environments and vigorouslyengaged in its new challenges. Interacting with, assisting, serving, and exploring with humans, the emerging robots will - creasingly touch people and their lives. Beyond its impact on physical robots, the body of knowledge robotics has produced is revealing a much wider range of applications reaching across - verse research areas and scienti c disciplines, such as: biomechanics, haptics, neurosciences, virtual simulation, animation, surgery, and sensor networks among others. In return, the challenges of the new emerging areas are pr- ing an abundant source of stimulation and insights for the eld of robotics. It is indeed at the intersection of disciplines that the most striking advances happen. TheSpringerTractsinAdvancedRobotics(STAR)isdevotedtobringingto the research community the latest advances in the robotics eld on the basis of their signi cance and quality. Through a wide and timely dissemination of critical research developments in robotics, our objective with this series is to promotemoreexchangesandcollaborationsamongtheresearchersinthec- munity and contributeto further advancements inthis rapidlygrowing eld. The monographwritten byAlejandro DizanVasquez Goveafocusesonthe practicalproblem of moving in a cluttered environment with pedestrians and vehicles. A frameworkbased on Hidden Markov models is developed to learn typical motion patterns which can be used to predict motion on the basis of sensor data. All the theoretical results have been implemented and validated with experiments, using both real and simulated data.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 176 pp. Englisch.

Bestandsnummer des Verkäufers 9783642136412

Bibliografische Details

• Titel: Incremental Learning for Motion Prediction of Pedestrians and Vehicles
• Verlag: Springer Berlin Heidelberg, Springer Berlin Heidelberg Jun 2010
• Erscheinungsjahr: 2010
• Sprache: Englisch
• ISBN-10: 3642136419
• ISBN-13: 9783642136412
• Einband: Buch
• Zustand: Neu
• Abmessungen: 241B x 160 H x 16 T Millimeter Breite: 241 mm, Höhe: 160 mm, Tiefe: 16 mm
• Gewicht: 468 Gramm

Über diesen Titel

Inhaltsangabe

This book focuses on the problem of moving in a cluttered environment with pedestrians and vehicles. A framework based on Hidden Markov models is developed to learn typical motion patterns which can be used to predict motion on the basis of sensor data.

Von der hinteren Coverseite

Modeling and predicting human and vehicle motion is an active research domain. Owing to the difficulty in modeling the various factors that determine motion (e.g. internal state, perception) this is often tackled by applying machine learning techniques to build a statistical model, using as input a collection of trajectories gathered through a sensor (e.g. camera, laser scanner), and then using that model to predict further motion. Unfortunately, most current techniques use offline learning algorithms, meaning that they are not able to learn new motion patterns once the learning stage has finished.

This books presents a lifelong learning approach where motion patterns can be learned incrementally, and in parallel with prediction. The approach is based on a novel extension to hidden Markov models, and the main contribution presented in this book, called growing hidden Markov models, which gives us the ability to learn incrementally both the parameters and the structure of the model. The proposed approach has been extensively validated with synthetic and real trajectory data. In our experiments our approach consistently learned motion models that were more compact and accurate than those produced by two other state-of-the-art techniques, confirming the viability of lifelong learning approaches to build human behavior models.