Search: onr:"swepub:oai:DiVA.org:kth-320423" >
Foresee the Unseen :
Foresee the Unseen : Sequential Reasoning about Hidden Obstacles for Safe Driving
-
- Gaspar Sánchez, José Manuel (author)
- KTH,Mekatronik,Digital Futures
-
- Nyberg, Truls (author)
- KTH,Robotik, perception och lärande, RPL,Scania CV AB, S-15187 Södertälje, Sweden.,Digital Futures
-
- Pek, Christian (author)
- KTH,Robotik, perception och lärande, RPL,Digital Futures
-
show more...
-
- Tumova, Jana (author)
- KTH,Robotik, perception och lärande, RPL
-
- Törngren, Martin, 1963- (author)
- KTH,Mekatronik,Digital Futures
-
show less...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2022
- 2022
- English.
-
In: 2022 IEEE Intelligent Vehicles Symposium (IV). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 255-264
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Safe driving requires autonomous vehicles to anticipate potential hidden traffic participants and other unseen objects, such as a cyclist hidden behind a large vehicle, or an object on the road hidden behind a building. Existing methods are usually unable to consider all possible shapes and orientations of such obstacles. They also typically do not reason about observations of hidden obstacles over time, leading to conservative anticipations. We overcome these limitations by (1) modeling possible hidden obstacles as a set of states of a point mass model and (2) sequential reasoning based on reachability analysis and previous observations. Based on (1), our method is safer, since we anticipate obstacles of arbitrary unknown shapes and orientations. In addition, (2) increases the available drivable space when planning trajectories for autonomous vehicles. In our experiments, we demonstrate that our method, at no expense of safety, gives rise to significant reductions in time to traverse various intersection scenarios from the CommonRoad Benchmark Suite.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database