Multifunctional Whisker Arrays for Distance Detection, Terrain Mapping, and Object Feature Extraction

Schultz, Alfred; Solomon, Joseph H.; Peshkin, Michael A.; Hartmann, Mitra J. Z.

doi:10.1109/robot.2005.1570503

Cited by 34 publications

(37 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another type of feel sensor is the artificial robotic whisker developed by Schultz et al [16] that can accurately sense different shapes and textures. It has been developed to mimic the way animals, such as rats use their whiskers to build up a picture of their environment and to test the hardness of objects.…”

Section: Current Work On Touch/feel Sensorsmentioning

confidence: 99%

Improving the Mobility Performance of Autonomous Unmanned Ground Vehicles by Adding the Ability to ‘Sense/Feel‘ Their Local Environment

2007

View full text Add to dashboard Cite

Abstract. This paper explores how a 'learning' algorithm can be added to UGV's by giving it the ability to test the terrain through 'feeling' using incorporated sensors, which would in turn increase its situational awareness. Once the conditions are measured the system will log the results and a database can be built up of terrain types and their properties (terrain classification), therefore when it comes to operating autonomously in an unknown, unpredictable environment, the vehicle will be able to cope by identifying the terrain and situation and then decide on the best and most efficient way to travel over it by making adjustments, which would greatly improve the vehicles ability to operate autonomously.

show abstract

Section: Current Work On Touch/feel Sensorsmentioning

confidence: 99%

Improving the Mobility Performance of Autonomous Unmanned Ground Vehicles by Adding the Ability to ‘Sense/Feel‘ Their Local Environment

2007

View full text Add to dashboard Cite

show abstract

“…Proof that navigation from such sensors is possible is readily found in biology: rats navigate through dark underground tunnels using their whiskers [7,2], having ranges of only a few centimetres. In robotics, whisker sensors are relatively cheap in both material and computational processing terms, and their use has previously been considered in constrained tasks [44,43,30,29,15]. The previous robotic attempts at mapping from sparse local sensors have either used the extremely strong generic prior that the whole world is made entirely of north-south and east-west straight edges [53] or have used relatively long range but sparse ray sensors integrated over multiscans [3].…”

Section: Introductionmentioning

confidence: 99%

Towards hierarchical blackboard mapping on a whiskered robot

Fox

Evans

Pearson

et al. 2012

Robotics and Autonomous Systems

View full text Add to dashboard Cite

The paradigm case for robotic mapping assumes large quantities of sensory information which allow the use of relatively weak priors. In contrast, the present study considers the mapping problem for a mobile robot, CrunchBot, where only sparse, local tactile information from whisker sensors is available. To compensate for such weak likelihood information, we make use of low-level signal processing and strong hierarchical object priors. Hierarchical models were popular in classical blackboard systems but are here applied in a Bayesian setting as a mapping algorithm. The hierarchical models require reports of whisker distance to contact and of surface orientation at contact, and we demonstrate that this information can be retrieved by classifiers from strain data collected by CrunchBot's physical whiskers. We then provide a demonstration in simulation of how this information can be used to build maps (but not yet full SLAM) in an zero-odometry-noise environment containing walls and table-like hierarchical objects.

show abstract

“…In robotics, touch sensors are relatively cheap in both material and computational processing terms, and their use has previously been considered to enhance navigation in cheap household robots [5], [6]. (Related work on research robot platforms includes [7], [8], [9], [10], [11]). …”

Section: Introductionmentioning

confidence: 99%

Mapping with Sparse Local Sensors and Strong Hierarchical Priors

Fox

Prescott

2011

Towards Autonomous Robotic Systems

View full text Add to dashboard Cite

Abstract-The paradigm case for robotic mapping, as in Simultaneous Localisation and Mapping problems, considers a mobile robot with noisy odometry and laser scanners. Laser scanners provide large amounts of sensory information, and have effectively unlimited range in indoor environments. Such large quantities of input information allow the use of relatively weak priors. In contrast, the present study considers the mapping problem in environments where only sparse, local sensory information is available. To compensate for the lack of likelihood evidence, we make use of strong hierarchical object priors. Hierarchical models were popular in classical blackboard systems but hare here applied in a Bayesian setting and novelly deployed as a mapping algorithm. We give proof of concept results, intended to demonstrate the algorithm's applicability as a part of a tactile SLAM module for the whiskered ScratchBot mobile robot platform. I. INTRODUCTIONThe paradigm case for robotic mapping, as in Simultaneous Localisation and Mapping (SLAM) problems [1], considers a mobile robot with noisy odometry and SICK laser scanners. Laser scanners provide large amounts of sensory information, and have effectively unlimited range in indoor environments. Such large quantities of input information allow the use of relatively weak priors, such as independent grid cell occupancy or flat priors over the belief of small feature sets [1].In contrast, the present study considers the mapping problem in environments where only sparse, local sensory information is available. For example, a fire-fighting robot building up a map in a smoke-filled house cannot rely on laser scanners functioning at all times, and could instead operate by feeling its way around with touch sensors. Proof that this type of navigation is possible is found in biology: electric fish make use of highly localised electric field sensors [2] and rats navigate through dark underground tunnels using their whiskers [3], [4], both having ranges of a few centimetres. In robotics, touch sensors are relatively cheap in both material and computational processing terms, and their use has previously been considered to enhance navigation in cheap household robots [5]

show abstract

Multifunctional Whisker Arrays for Distance Detection, Terrain Mapping, and Object Feature Extraction

Cited by 34 publications

References 19 publications

Improving the Mobility Performance of Autonomous Unmanned Ground Vehicles by Adding the Ability to ‘Sense/Feel‘ Their Local Environment

Improving the Mobility Performance of Autonomous Unmanned Ground Vehicles by Adding the Ability to ‘Sense/Feel‘ Their Local Environment

Towards hierarchical blackboard mapping on a whiskered robot

Mapping with Sparse Local Sensors and Strong Hierarchical Priors

Contact Info

Product

Resources

About