Stage-oe-small.jpg

Neuigkeit108: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
 
Zeile 2: Zeile 2:
 
|Titel DE=Best Paper Award - IEEE International Conference on Intelligent Transportation Systems (ITSC)
 
|Titel DE=Best Paper Award - IEEE International Conference on Intelligent Transportation Systems (ITSC)
 
|Titel EN=Best Paper Award - IEEE International Conference on Intelligent Transportation Systems (ITSC)
 
|Titel EN=Best Paper Award - IEEE International Conference on Intelligent Transportation Systems (ITSC)
 +
|Beschreibung DE='''Holger Banzhaf wurde für seine Arbeit ''From Footprints to Beliefprints: Motion Planning under Uncertainty for Maneuvering Automated Vehicles in Dense Scenarios'' auf der ITSC 2018 mit dem Best Paper Award ausgezeichnet.'''<br><br>'''Abstract'''<br>Motion planning for car-like robots is one of the major challenges in automated driving. It requires to solve a two-point boundary value problem that connects a start and a goal configuration with a collision-free trajectory. This paper introduces a novel approach for motion planning under uncertainty resulting in motion plans with higher robustness due to a bounded risk of collision. To that end, the state of the art G1 and G2 continuous steering functions, namely Dubins, Reeds-Shepp, Hybrid Curvature, and Continuous Curvature Steer, are extended to belief space, where an expected vehicle state is augmented by its associated uncertainty. The so-called beliefs are obtained by propagating a Gaussian probability distribution along the nominal path of the steering function while taking into account the control and localization uncertainty. A novel concept for collision avoidance in Gaussian belief space is then introduced that considers the shape of the vehicle and the full information about the uncertainty of a state. Together with the sampling-based motion planner RRT*, the proposed real-time capable methodology reduces the collision probability by an order of magnitude in three challenging automated driving scenarios.
 +
|Beschreibung EN='''Holger Banzhaf was awarded with the Best Paper Award for his paper named ''From Footprints to Beliefprints: Motion Planning under Uncertainty for Maneuvering Automated Vehicles in Dense Scenarios'' at ITSC 2018.'''<br><br>'''Abstract'''<br>Motion planning for car-like robots is one of the major challenges in automated driving. It requires to solve a two-point boundary value problem that connects a start and a goal configuration with a collision-free trajectory. This paper introduces a novel approach for motion planning under uncertainty resulting in motion plans with higher robustness due to a bounded risk of collision. To that end, the state of the art G1 and G2 continuous steering functions, namely Dubins, Reeds-Shepp, Hybrid Curvature, and Continuous Curvature Steer, are extended to belief space, where an expected vehicle state is augmented by its associated uncertainty. The so-called beliefs are obtained by propagating a Gaussian probability distribution along the nominal path of the steering function while taking into account the control and localization uncertainty. A novel concept for collision avoidance in Gaussian belief space is then introduced that considers the shape of the vehicle and the full information about the uncertainty of a state. Together with the sampling-based motion planner RRT*, the proposed real-time capable methodology reduces the collision probability by an order of magnitude in three challenging automated driving scenarios.
 
|Datum=2018/11/05
 
|Datum=2018/11/05
|Beschreibung DE='''Holger Banzhaf was awarded with the Best Paper Award for his paper named ''From Footprints to Beliefprints: Motion Planning under Uncertainty for Maneuvering Automated Vehicles in Dense Scenarios'' at ITSC 2018.'''<br><br>'''Abstract'''<br>Motion planning for car-like robots is one of the major challenges in automated driving. It requires to solve a two-point boundary value problem that connects a start and a goal configuration with a collision-free trajectory. This paper introduces a novel approach for motion planning under uncertainty resulting in motion plans with higher robustness due to a bounded risk of collision. To that end, the state of the art G1 and G2 continuous steering functions, namely Dubins, Reeds-Shepp, Hybrid Curvature, and Continuous Curvature Steer, are extended to belief space, where an expected vehicle state is augmented by its associated uncertainty. The so-called beliefs are obtained by propagating a Gaussian probability distribution along the nominal path of the steering function while taking into account the control and localization uncertainty. A novel concept for collision avoidance in Gaussian belief space is then introduced that considers the shape of the vehicle and the full information about the uncertainty of a state. Together with the sampling-based motion planner RRT*, the proposed real-time capable methodology reduces the collision probability by an order of magnitude in three challenging automated driving scenarios.
 
|Beschreibung EN='''Holger Banzhaf was awarded with the Best Paper Award for his paper named ''From Footprints to Beliefprints: Motion Planning under Uncertainty for Maneuvering Automated Vehicles in Dense Scenarios'' at ITSC 2018.'''<br><br>'''Abstract'''<br>Motion planning for car-like robots is one of the major challenges in automated driving. It requires to solve a two-point boundary value problem that connects a start and a goal configuration with a collision-free trajectory. This paper introduces a novel approach for motion planning under uncertainty resulting in motion plans with higher robustness due to a bounded risk of collision. To that end, the state of the art G1 and G2 continuous steering functions, namely Dubins, Reeds-Shepp, Hybrid Curvature, and Continuous Curvature Steer, are extended to belief space, where an expected vehicle state is augmented by its associated uncertainty. The so-called beliefs are obtained by propagating a Gaussian probability distribution along the nominal path of the steering function while taking into account the control and localization uncertainty. A novel concept for collision avoidance in Gaussian belief space is then introduced that considers the shape of the vehicle and the full information about the uncertainty of a state. Together with the sampling-based motion planner RRT*, the proposed real-time capable methodology reduces the collision probability by an order of magnitude in three challenging automated driving scenarios.
 
 
|Forschungsgruppe=Angewandte Technisch-Kognitive Systeme
 
|Forschungsgruppe=Angewandte Technisch-Kognitive Systeme
 
}}
 
}}

Aktuelle Version vom 18. Dezember 2018, 09:46 Uhr

Neuigkeit vom 5. November 2018


Best Paper Award - IEEE International Conference on Intelligent Transportation Systems (ITSC)


Holger Banzhaf wurde für seine Arbeit From Footprints to Beliefprints: Motion Planning under Uncertainty for Maneuvering Automated Vehicles in Dense Scenarios auf der ITSC 2018 mit dem Best Paper Award ausgezeichnet.

Abstract
Motion planning for car-like robots is one of the major challenges in automated driving. It requires to solve a two-point boundary value problem that connects a start and a goal configuration with a collision-free trajectory. This paper introduces a novel approach for motion planning under uncertainty resulting in motion plans with higher robustness due to a bounded risk of collision. To that end, the state of the art G1 and G2 continuous steering functions, namely Dubins, Reeds-Shepp, Hybrid Curvature, and Continuous Curvature Steer, are extended to belief space, where an expected vehicle state is augmented by its associated uncertainty. The so-called beliefs are obtained by propagating a Gaussian probability distribution along the nominal path of the steering function while taking into account the control and localization uncertainty. A novel concept for collision avoidance in Gaussian belief space is then introduced that considers the shape of the vehicle and the full information about the uncertainty of a state. Together with the sampling-based motion planner RRT*, the proposed real-time capable methodology reduces the collision probability by an order of magnitude in three challenging automated driving scenarios.



Aus der Forschungsgruppe Angewandte Technisch-Kognitive Systeme