2005 IEEE/RSJ International Conference on Intelligent Robots and Systems 2005
DOI: 10.1109/iros.2005.1545026
|View full text |Cite
|
Sign up to set email alerts
|

Supervised machine learning for modeling human recognition of vehicle-driving situations

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2009
2009
2022
2022

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 10 publications
0
4
0
Order By: Relevance
“…While these are very promising avenues to pursue, we feel that we can offer powerful driver-assistance tools by intelligently analyzing readily available sensors on commercial vehicles to determine how the current situation can impact driver performance. Unsupervised learning has been used as a basis for context recognition for mobile devices [10] and for improving image classification [11] The work presented in this paper extends the previous work in driving-difficulty systems of [12], which trained a classification system to identify potentially dangerous driving conditions using predefined situations. This system identified eight highlevel situations with high accuracy: 1) Approaching or Waiting at Intersection, 2) Leaving Intersection, 3) Entering On-ramp or High-Speed Roadway, 4) Being Overtaken, 5) High Acceleration or Dynamic State of Vehicle, 6) Approaching Slow-Moving Vehicle, 7) Preparing to Change Lanes, and 8) Changing Lanes.…”
Section: Related Workmentioning
confidence: 80%
See 1 more Smart Citation
“…While these are very promising avenues to pursue, we feel that we can offer powerful driver-assistance tools by intelligently analyzing readily available sensors on commercial vehicles to determine how the current situation can impact driver performance. Unsupervised learning has been used as a basis for context recognition for mobile devices [10] and for improving image classification [11] The work presented in this paper extends the previous work in driving-difficulty systems of [12], which trained a classification system to identify potentially dangerous driving conditions using predefined situations. This system identified eight highlevel situations with high accuracy: 1) Approaching or Waiting at Intersection, 2) Leaving Intersection, 3) Entering On-ramp or High-Speed Roadway, 4) Being Overtaken, 5) High Acceleration or Dynamic State of Vehicle, 6) Approaching Slow-Moving Vehicle, 7) Preparing to Change Lanes, and 8) Changing Lanes.…”
Section: Related Workmentioning
confidence: 80%
“…We have conducted a series of driving experiments in unstructured environments over the past several years. The first studies were a proof of concept that we could infer difficult driving situation from readily available sensors from a commercial vehicle in naturalistic on-road driving conditions [12]. The set of experiments covered by this analysis involved driving in off-road conditions, on semi-improved and unimproved paths, at the United States Marine Corps Base Camp Pendleton.…”
Section: Experimental Descriptionmentioning
confidence: 99%
“…Different aspects were analyzed by [12,13] in their studies. In particular, [12] exploited machine learning to model human recognition of vehicle-driving situations.…”
Section: Background and Related Workmentioning
confidence: 99%
“…Different aspects were analyzed by [12,13] in their studies. In particular, [12] exploited machine learning to model human recognition of vehicle-driving situations. The purpose of such research is to provide physical context to mitigate unnecessary distractions, allowing the driver to maintain focus during periods that require high concentration.…”
Section: Background and Related Workmentioning
confidence: 99%