Object Matching for Inter-Vehicle Communication Systems—An IMM-Based Track Association Approach With Sequential Multiple Hypothesis Test

Yuan, Ting; Krishnan, Krishanth; Chen, Qi; Breu, Jakob; Roth, Tobias; Duraisamy, Bharanidhar; Weiss, Christian; Maile, Michael; Gern, Axel

doi:10.1109/tits.2017.2723894

Cited by 29 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The vehicle positioning approaches in the literature can be classified into two categories: the relative positioning [ 10 , 11 , 12 , 13 , 14 ] and the absolute positioning [ 7 , 8 , 9 , 15 , 16 , 24 , 25 , 26 , 27 , 28 , 32 ]. Table 1 summarizes a few different approaches to vehicle positioning.…”

Section: Related Workmentioning

confidence: 99%

“…In this representation, the lack of absolute position reference is still acceptable, provided that the exteroceptive sensor can accurately track the relative states of all moving objects, called the targets. A tracking filter is usually employed to minimize the mean square error of the target state against the high mobility of vehicles, the obstruction of sensor signals, and the random reflection from road surface and environments, called the clutters [ 13 , 14 , 33 ].…”

Section: Related Workmentioning

confidence: 99%

“…In [ 33 ], an unscented Kalman filter (UKF) is designed for the radar of a moving vehicle that tracks the targets by taking both radar measurements and V2X communications as the measurement inputs. An alternative approach is to use the interacting multiple models (IMM) for driving behaviors and the sequential multiple hypothesis tests for associating radar measurement and V2X communications [ 14 ]. However, the intensive computation involved in the state estimation and the data association limits its applicability to simultaneously track many surrounding vehicles.…”

Section: Related Workmentioning

confidence: 99%

“…In the last decade, the automotive industry has commercialized many on-board exteroceptive sensors, such as radars, cameras, and laser scanners, for estimating the relative state of surrounding objects [ 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 ]. This estimate is called the local sensing estimate (LSE) in this paper.…”

Section: Introductionmentioning

confidence: 99%

“…The richness and high precision of these devices make it possible to estimate both relative and absolute positionings with high accuracy [ 10 ]. In detail, the relative positioning of each surrounding vehicle is a key parameter of collision risk assessment [ 10 , 11 , 12 ], whereas the absolute positioning with high-precision environment map is the essential functionality of autonomous driving [ 13 , 14 , 15 , 16 ]. The primary goal of this paper is to improve the accuracy of absolute positioning without high-precision environment map.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Spatiotemporal Local-Remote Senor Fusion (ST-LRSF) for Cooperative Vehicle Positioning

Jeong

Nguyen

Bhawiyuga

2018

Sensors

View full text Add to dashboard Cite

Vehicle positioning plays an important role in the design of protocols, algorithms, and applications in the intelligent transport systems. In this paper, we present a new framework of spatiotemporal local-remote sensor fusion (ST-LRSF) that cooperatively improves the accuracy of absolute vehicle positioning based on two state estimates of a vehicle in the vicinity: a local sensing estimate, measured by the on-board exteroceptive sensors, and a remote sensing estimate, received from neighbor vehicles via vehicle-to-everything communications. Given both estimates of vehicle state, the ST-LRSF scheme identifies the set of vehicles in the vicinity, determines the reference vehicle state, proposes a spatiotemporal dissimilarity metric between two reference vehicle states, and presents a greedy algorithm to compute a minimal weighted matching (MWM) between them. Given the outcome of MWM, the theoretical position uncertainty of the proposed refinement algorithm is proven to be inversely proportional to the square root of matching size. To further reduce the positioning uncertainty, we also develop an extended Kalman filter model with the refined position of ST-LRSF as one of the measurement inputs. The numerical results demonstrate that the proposed ST-LRSF framework can achieve high positioning accuracy for many different scenarios of cooperative vehicle positioning.

show abstract