A study of visual and tactile terrain classification and classifier fusion for planetary exploration rovers

Halatci, Ibrahim; Brooks, Christopher; Iagnemma, Karl

doi:10.1017/s0263574708004360

Cited by 32 publications

(28 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also presented a method to classify terrains based on vibrations measured by an accelerometer installed on the rover, which is robust against lighting variations as compared to the vision-based method [61]. Halatci et al [62] studied the performance of multisensor classification methods, and combined the visual and tactile classification methods for Mars surface exploration. The effectiveness of these approaches were verified using experimental results from the four-wheeled rover testbed and the single-wheel testbed.…”

Section: Current Research On Planetary Rovers' Terramechanicsmentioning

confidence: 99%

Planetary rovers’ wheel–soil interaction mechanics: new challenges and applications for wheeled mobile robots

Ding

Deng

Gao

et al. 2010

Intel Serv Robotics

View full text Add to dashboard Cite

With the increasing challenges facing planetary exploration missions and the resultant increase in the performance requirements for planetary rovers, terramechanics (wheel-soil interaction mechanics) is playing an important role in the development of these rovers. As an extension of the conventional terramechanics theory for terrestrial vehicles, the terramechanics theory for planetary rovers, which is becoming a new research hotspot, is unique and puts forward many new challenging problems. This paper first discusses the significance of the study of wheel-soil interaction mechanics of planetary rovers and summarizes the differences between planetary rovers and terrestrial vehicles and the problems arising thereof. The application of terramechanics to the development of planetary rovers can be divided into two phases (the R&D phase and exploration phase for rovers) corresponding to the high-fidelity and simplified terramechanics models. This paper also describes the current research status by providing an introduction to classical terramechanics and the experimental, theoretical, and numerical researches on terramechanics for planetary rovers. The application status of the terramechanics for planetary rovers is analyzed from the aspects of rover design, performance evaluation, planetary soil parameter identification, dynamics simulation, mobility control, and path planning. Finally, the key issues for future research are discussed. The current planetary rovers are actually advanced wheeled mobile robots (WMRs), developed employing cutting-edge technologies from different fields. The terramechanics for planetary rovers is expected to present new challenges and applications for WMRs, making it possible to develop WMRs using the concepts of mechanics and dynamics.

show abstract

Section: Current Research On Planetary Rovers' Terramechanicsmentioning

confidence: 99%

Planetary rovers’ wheel–soil interaction mechanics: new challenges and applications for wheeled mobile robots

Ding

Deng

Gao

et al. 2010

Intel Serv Robotics

View full text Add to dashboard Cite

show abstract

“…The use of terrain classification and characterization for navigation purposes has been done by (Manduchi et al, 2005), (Halatci et al, 2008), (Talukder et al, 2002), (Dima et al, 2004). (Halatci et al, 2008) specifically addresses the challenges of terrain classification for planetary rovers.…”

Section: Related Workmentioning

confidence: 99%

“…(Halatci et al, 2008) specifically addresses the challenges of terrain classification for planetary rovers. None of these papers, however, specifically address the integration of the terrain classification with a path planner.…”

Section: Related Workmentioning

confidence: 99%

Terrain Adaptive Navigation for planetary rovers

Helmick

Angelova

Matthies

2009

Journal of Field Robotics

View full text Add to dashboard Cite

This paper describes the design, implementation, and experimental results of a navigation system for planetary rovers called Terrain Adaptive Navigation (TANav). This system was designed to enable greater access to and more robust operations within terrains of widely varying slippage. The system achieves this goal by using onboard stereo cameras to remotely classify surrounding terrain, predict the slippage of that terrain, and use this information in the planning of a path to the goal. This navigation system consists of several integrated techniques: goodness map generation, terrain triage, terrain classification, remote slip prediction, path planning, high-fidelity traversability analysis (HFTA), and slip-compensated path following. Results from experiments with an end-to-end onboard implementation of the TANav system in a Mars analog environment are shown and compared to results from experiments with a more traditional navigation system that does not account for terrain properties.

show abstract

“…The authors propose a Gaussian mixture model for detection and classification of novel terrains. Halatci, Brooks, and Iagnemma (2008) propose a classification method making use of both visual and vibration data, comparing several classification methods. It shows great results in classifying terrains encountered, but fundamentally the process is a supervised one.…”

Section: State Of the Artmentioning

confidence: 99%

Adaptive rover behavior based on online empirical evaluation: Rover–terrain interaction and near‐to‐far learning

Krebs

Pradalier

Siegwart

2009

Journal of Field Robotics

View full text Add to dashboard Cite

Owing to the fundamental nature of all-terrain exploration, autonomous rovers are confronted with unknown environments. This is especially apparent regarding soil interactions, as the nature of the soil is typically unknown. This work aims at establishing a framework from which the rover can learn from its interaction with the terrains encountered and shows the importance of such a method. We introduce a set of rover-terrain interaction (RTI) and remote data metrics that are expressed in different subspaces. In practice, the information characterizing the terrains, obtained from remote sensors (e.g., a camera) and local sensors (e.g., an inertial measurement unit) is used to characterize the respective remote data and RTI model. In each subspace, which can be described as a feature space encompassing either a remote data measurement or an RTI, similar features are grouped to form classes, and the probability distribution function over the features is learned for each one of those classes. Subsequently, data acquired on the same terrain are used to associate the corresponding models in each subspace and to build an inference model. Based on the remote sensor data measured, the RTI model is predicted using the inference model. This process corresponds to a near-to-far approach and provides the most probable RTI metrics of the terrain lying ahead of the rover. The predicted RTI metrics are then used to plan an optimal path with respect to the RTI model and therefore influence the rover trajectory. The CRAB rover is used in this work for the implementation and testing of the approach, which we call rover-terrain interactions learned from experiments (RTILE). This article presents RTILE, describes its implementation, and concludes with results from field tests that validate the approach. C 2009 Wiley Periodicals, Inc.• First, the performance depends on the robot's physical and mechanical properties, corresponding to its structure, suspension mechanism, actuators, and sensors.• Second, the performance is related to the control of the robotic platform, in a very generic sense. This includes research in fields such as control, obstacle avoidance, path planning, pose estimation, and so forth.As mentioned in the latter point, the robot's performance is related to the interaction of the robot with its surroundings and its capability to sense and represent the environment. A natural environment, which is usually the operating place for all-terrain rovers, involves a great diversity in terrain, soil and obstacle types, shapes, and appearances. This diversity is difficult to model and hence implies additional uncertainty that the rover must cope with.

show abstract

A study of visual and tactile terrain classification and classifier fusion for planetary exploration rovers

Cited by 32 publications

References 33 publications

Planetary rovers’ wheel–soil interaction mechanics: new challenges and applications for wheeled mobile robots

Planetary rovers’ wheel–soil interaction mechanics: new challenges and applications for wheeled mobile robots

Terrain Adaptive Navigation for planetary rovers

Adaptive rover behavior based on online empirical evaluation: Rover–terrain interaction and near‐to‐far learning

Contact Info

Product

Resources

About