Independent Markov chain occupancy grid maps for representation of dynamic environment

Saarinen, Jyrki; Andreasson, Henrik; Lilienthal, Achim J.

doi:10.1109/iros.2012.6385629

Cited by 75 publications

(58 citation statements)

References 13 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Saarinen at al. [5] model a dynamic environment as an occupancy grid with associated independent Markov chains for every cell on the grid. Patch Maps [6] represents the different observed states of parts of the map and selects the one most similar to the robot's observation for localization.…”

Section: Related Workmentioning

confidence: 99%

Model-Instance Object Mapping

Biswas

Veloso

2015

RoboCup 2014: Robot World Cup XVIII

View full text Add to dashboard Cite

Abstract. Robot localization and mapping algorithms commonly represent the world as a static map. In reality, human environments consist of many movable objects like doors, chairs and tables. Recognizing that such environment often have a large number of instances of a small number of types of objects, we propose an alternative approach, Model-Instance Object Mapping that reasons about the models of objects distinctly from their different instances. Observations classified as short-term features by Episodic non-Markov Localization are clustered to detect object instances. For each object instance, an occupancy grid is constructed, and compared to every other object instance to build a directed similarity graph. Common object models are discovered as strongly connected components of the graph, and their models as well as distribution of instances saved as the final Model-Instance Object Map. By keeping track of the poses of observed instances of object models, Model-Instance Object Maps learn the most probable locations for commonly observed object models. We present results of Model-Instance Object Mapping over the course of a month in our indoor office environment, and highlight the common object models thus learnt in an unsupervised manner.

show abstract

Section: Related Workmentioning

confidence: 99%

Model-Instance Object Mapping

Biswas

Veloso

2015

RoboCup 2014: Robot World Cup XVIII

View full text Add to dashboard Cite

show abstract

“…We first explain about the IMAC model [5] . The proposed algorithm is given in the next sub-sections: the grid update algorithm and the propose method for anomalous stop detection.…”

Section: Approach For Map Generation and Anomaly Detectionmentioning

confidence: 99%

“…The IMAC [5] is an occupancy grid map based on the proposed model of Luber [4] . Each grid has two states, which being in occupied or free.…”

Section: Independent Markov Chain Occupancy Grid Map (Imac)mentioning

confidence: 99%

See 1 more Smart Citation

Anomaly Stop Detection by Smartphone

Dang¹,

Kubo²,

Satō³

et al. 2014

JRNAL

View full text Add to dashboard Cite

This paper proposes a method for detecting anomaly stop events from GPS logs of a vehicle recorded by smartphone. Despite of many researches of strong braking event detection are proposed, they cannot discriminate between a normal and an abnormal braking event. Our proposal includes an IMAC model for GPS based map generation and an algorithm for anomaly stops detection based on the acquired map. The real world experiment shows our map generation method and its anomaly stop detection rule works well.

show abstract

“…In this paper we present a method that allows an autonomous robot to iteratively learn to distinguish between 1 The authors are all with the Centre for Autonomous Systems at KTH Royal Institute of Technology, Stockholm, SE-100 44, Sweden.…”

Section: Introductionmentioning

confidence: 99%

Meta-rooms: Building and maintaining long term spatial models in a dynamic world

Ambruş

Bore

Folkesson

et al. 2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-We present a novel method for re-creating the static structure of cluttered office environments -which we define as the "meta-room" -from multiple observations collected by an autonomous robot equipped with an RGB-D depth camera over extended periods of time. Our method works directly with point clusters by identifying what has changed from one observation to the next, removing the dynamic elements and at the same time adding previously occluded objects to reconstruct the underlying static structure as accurately as possible. The process of constructing the meta-rooms is iterative and it is designed to incorporate new data as it becomes available, as well as to be robust to environment changes. The latest estimate of the meta-room is used to differentiate and extract clusters of dynamic objects from observations. In addition, we present a method for re-identifying the extracted dynamic objects across observations thus mapping their spatial behaviour over extended periods of time.

show abstract

Independent Markov chain occupancy grid maps for representation of dynamic environment

Cited by 75 publications

References 13 publications

Model-Instance Object Mapping

Model-Instance Object Mapping

Anomaly Stop Detection by Smartphone

Meta-rooms: Building and maintaining long term spatial models in a dynamic world

Contact Info

Product

Resources

About