Vision-based cooperative simultaneous localization and tracking

Chang, Chun-Hua; Wang, Shao-Chen; Wang, Chieh-Chih

doi:10.1109/icra.2011.5980505

Cited by 22 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In multi-robot cooperative perception, measurement-based algorithms have been proposed such as the particle filter (PF) based approach [4], the maximum likelihood estimation (MLE) based approach [6], and the extended Kalman filter (EKF) based approach [8]. In these approaches, measurements, e.g.…”

Section: Related Workmentioning

confidence: 99%

“…With the ability to detect other robots, multi-robot cooperative localization has been proved to effectively outperform single-robot localization by incorporating relative measurements between a troop of robots [4][5] [6]. In addition, it has also been demonstrated that multi-robot simultaneous localization and tracking (MR-SLAT) can further improve the performance by exploiting the relative measurements between robots and moving objects in dynamic scenes [7] [8].…”

Section: Introductionmentioning

confidence: 99%

“…In measurement-based approaches [4][6] [8], the control data and measurements are shared once after they are fetched. With well-controlled communication, in which the packet loss rate is low and there are merely consecutive packets lost, each robot is expected to receive all control data and measurements from the other robots, and the global state is inferred in a centralized manner.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Communication adaptive multi-robot simultaneous localization and tracking via hybrid measurement and belief sharing

Chang

Wang³

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Existing multi-robot cooperative perception solutions can be mainly classified into two categories, measurement-based and belief-based, according to the information shared among robots. With well-controlled communication, measurement-based approaches are expected to achieve theoretically optimal estimates while belief-based approaches are not because the cross-correlations between beliefs are hard to be perfectly estimated in practice. Nevertheless, belief-based approaches perform relatively stable under unstable communication as a belief contains the information of multiple previous measurements. Motivated by the observation that measurement sharing and belief sharing are respectively superior in different conditions, in this paper a hybrid algorithm, communication adaptive multi-robot simultaneous localization and tracking (ComAd MR-SLAT), is proposed to combine the advantages of both. To tackle the unknown or unstable communication conditions, the information to share is decided by maximizing the expected uncertainty reduction online, based on which the algorithm dynamically alternates between measurementsharing and belief-sharing without information loss or reuse. The proposed ComAd MR-SLAT is evaluated in communication conditions with different packet loss rates and bursty loss lengths. In our experiments, ComAd MR-SLAT outperforms measurement-based and belief-based MR-SLAT in accuracy. The experimental results demonstrate the effectiveness of the proposed hybrid algorithm and exhibit that ComAd MR-SLAT is robust under different communication conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Communication adaptive multi-robot simultaneous localization and tracking via hybrid measurement and belief sharing

Chang

Wang³

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Available collaborative localization (CL) schemes can be classified into three major groups, centralized, multi-centralized and decentralized CL approaches. Both the centralized [2] and multicentralized approaches [3] are promising for optimal solution to the CL problem; however, they demand higher computational cost and communication cost. Available decentralized approaches perform sensor fusion either in an optimal manner [4] or an approximate manner [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Distributed collaborative localization for a heterogeneous multi-robot system

Wanasinghe

Mann

Gosine

2014

2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE)

View full text Add to dashboard Cite

This paper studies the problem of collaborative localization for a heterogeneous multi-robotic system (MRS), particularly an MRS with one or more robots with accurate selflocalization capabilities (leader) and several robots with little or no such capabilities (child). Finite-range sensing is one of the major limitation in the collaboration of an MRS when the child robots rely on inter-robot relative measurements (IRRM) between themselves and the leader robot for localization. This study proposes a collaborative localization (CL) scheme, which has the ability to localize child robots even when they operate beyond the field of view (FOV) of the leader robots. A distributed sensor fusion architecture is introduced in order to reduce the communication bandwidth, processing power, and memory usage requirements for the leader robot. Thus, the resulting implementation is scalable in terms of the number of robots in the team. The performance of the proposed localization scheme was evaluated in Monte Carlo simulations and a series of experiments using a team of six mobile robots. Both the experiment and the simulation results demonstrated that the proposed CL scheme is capable of establishing a localization for child robots with 1∼10 cm positional accuracy and 0.01∼0.1 rad orientational accuracy, even when they operate beyond the FOV of the leader robot.

show abstract

“…between the nodes, an algorithm for simultaneous localizing and tracking vehicles [13] [14] is utilized to obtain sub-meter accurate localization which is necessary for driver warning systems. Second, for fusion within the nodes, algorithms to detect moving objects from laser scanner and stationary cameras is exploited to provide pedestrians, motorcycles, bikes, and cars information in the heterogeneous sensor fusion scheme.…”

Section: B Neighbor Map Buildingmentioning

confidence: 99%

Connected vehicle safety science, system, and framework

Chen

Tsai

Hsieh

et al. 2014

2014 IEEE World Forum on Internet of Things (WF-IoT)

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper, we propose a framework to develop an M2M-based (machine-to-machine) proactive driver assistance system. Unlike traditional approaches, we take the benefits of M2M in intelligent transportation system (ITS): 1) expansion of sensor coverage, 2) increase of time allowed to react, and 3) mediation of bidding for right of way, to help driver avoiding potential traffic accidents. To develop such a system, we divide it into three main parts: 1) driver behavior modeling and prediction, which collects grand driving data to learn and predict the future behaviors of drivers; 2) M2M-based neighbor map building, which includes sensing, communication, and fusion technologies to build a neighbor map, where neighbor map mentions the locations of all neighboring vehicles; 3) design of passive information visualization and proactive warning mechanism, which researches on how to provide user-needed information and warning signals to drivers without interfering their driving activities.

show abstract

Vision-based cooperative simultaneous localization and tracking

Cited by 22 publications

References 17 publications

Communication adaptive multi-robot simultaneous localization and tracking via hybrid measurement and belief sharing

Communication adaptive multi-robot simultaneous localization and tracking via hybrid measurement and belief sharing

Distributed collaborative localization for a heterogeneous multi-robot system

Connected vehicle safety science, system, and framework

Contact Info

Product

Resources

About