Automotive Collision Risk Estimation Under Cooperative Sensing

LaChapelle, Daniel M.; Humphreys, Todd E.; Narula, Lakshay; Iannucci, Peter A.; Moradi-Pari, Ehsan

doi:10.1109/icassp40776.2020.9053745

Cited by 9 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These limitations prompted the authors to find more appropriate solutions. For example, the authors in [75] considered the risk over a path to be a measure of the expected loss. The expectation, in this case, was taken over the probability that the vehicle will collide with an obstacle at cell c. Hence, the risk is expressed by the following:…”

Section: Risk Assessments Along a Path In Traversability Grid Mapsmentioning

confidence: 99%

A Review on Traversability Risk Assessments for Autonomous Ground Vehicles: Methods and Metrics

Benrabah,

Orou Mousse,

Randriamiarintsoa

et al. 2024

Sensors

View full text Add to dashboard Cite

Evaluating the risk associated with operations is an essential element of safe planning and an essential prerequisite in mobile robotics. This issue is very broad, with numerous definitions emerging in the recent literature adapting different application scenarios and leading to different algorithmic approaches. In this review, we will investigate how the state-of-the-art approaches define the traversability risk, particularly for mobile robots, whereby we classify existing risk-aware navigation algorithms according to their characterization of risk. Subsequently, we will overview the formulations of risk assessment along a path using traversability grid maps since it is essential for a mobile robot to evaluate its path to predict potential hazards. Finally, we will discuss the consistency of commonly used risk metrics in robotics. The aim of the review is to offer a comprehensive overview to newcomers in the field, to provide a structured reference for practitioners, and to also inspire future developments.

show abstract

Section: Risk Assessments Along a Path In Traversability Grid Mapsmentioning

confidence: 99%

A Review on Traversability Risk Assessments for Autonomous Ground Vehicles: Methods and Metrics

Benrabah,

Orou Mousse,

Randriamiarintsoa

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…where p pq (O | z k ) is known as the inverse sensor model: it describes the probability of c pq being in state O, given only the latest radar scan z k . The required occupancy probability p pq (O | z 1:k ) is easy to compute from the log odds ratio in (3). Observe that the inverse sensor model p pq (O | z k ), in addition to the prior occupancy belief p pq (O), completely describes the procedure for estimating the OGM from radar measurements, and hence approximating the PHD.…”

Section: B Estimating the Map Phd From Measurementsmentioning

confidence: 99%

“…Development of automated ground vehicles (AGVs) has spurred research in lane-keeping assist systems, automated intersection management [1], tight-formation platooning, and cooperative sensing [2], [3], all of which demand accurate (e.g., 50-cm at 95%) ground vehicle positioning in an urban environment. But the majority of positioning techniques developed thus far depend on lidar or cameras, which perform poorly in low-visibility conditions such as snowy whiteout, dense fog, or heavy rain.…”

Section: Introductionmentioning

confidence: 99%

Automotive-Radar-Based 50-cm Urban Positioning

Narula¹,

Iannucci²,

Humphreys³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deployment of automated ground vehicles (AGVs) beyond the confines of sunny and dry climes will require sub-lanelevel positioning techniques based on radio waves rather than near-visible-light radiation. Like human sight, lidar and cameras perform poorly in low-visibility conditions. This paper develops and demonstrates a novel technique for robust 50-cm-accurate urban ground positioning based on commercially-available lowcost automotive radars. The technique is computationally efficient yet obtains a globally-optimal translation and heading solution, avoiding local minima caused by repeating patterns in the urban radar environment. Performance is evaluated on an extensive and realistic urban data set. Comparison against ground truth shows that, when coupled with stable short-term odometry, the technique maintains 95-percentile errors below 50 cm in horizontal position and 1 • in heading.

show abstract

“…The challenge of developing automated ground vehicles (AGVs) has spurred research in lane-keeping assistance systems, automated intersection management [Fajardo et al, 2011], tight-formation platooning, and cooperative sensing [Choi et al, 2016, LaChapelle et al, 2020, all of which, in an urban environment, demand accurate (e.g., 50-cm) positioning. But the majority of positioning techniques developed thus far depend on LiDAR or cameras, which perform poorly in low-visibility conditions, such as snowy whiteout, dense fog, or heavy rain.…”

Section: Introductionmentioning

confidence: 99%

All-Weather, sub-50-cm, Radar-Inertial Positioning

Narula

Iannucci²,

Humphreys³

2022

Self Cite

View full text Add to dashboard Cite

Deploying automated ground vehicles beyond the confines of sunny and dry climes will require sub-lane-level positioning techniques that use radio waves, rather than near-visible light radiation. Like human sight, LiDAR and optical cameras perform poorly in low-visibility conditions. We present and demonstrate a novel technique for robust, sub-50-cm, urban ground vehicle positioning based on all-weather sensors. The technique incorporates a computationally-efficient, globally-optimal radar scan registration algorithm within a larger estimation pipeline that fuses data from commercially-available, low-cost, automotive radars, low-cost inertial sensors, vehicle motion constraints, and, when available, precise GNSS measurements. We evaluate the performance of the presented technique on an extensive and realistic urban dataset derived from all-weather sensors. Comparison against ground truth shows that during 60 min of GNSS-denied driving in the urban center of Austin, TX, the technique maintains 95th-percentile errors below 50 cm in horizontal position and 0.5 in heading.

show abstract

Automotive Collision Risk Estimation Under Cooperative Sensing

Cited by 9 publications

References 20 publications

A Review on Traversability Risk Assessments for Autonomous Ground Vehicles: Methods and Metrics

A Review on Traversability Risk Assessments for Autonomous Ground Vehicles: Methods and Metrics

Automotive-Radar-Based 50-cm Urban Positioning

All-Weather, sub-50-cm, Radar-Inertial Positioning

Contact Info

Product

Resources

About