Research on trajectory planning in emergency situations with multiple objects

IEEE Trans. Intell. Veh.

Magdici

2016

Abstract-Safety is of paramount importance in automated driving. One of the main challenges ensuring safety is the unknown future behavior of surrounding traffic participants. Previous works ignore this uncertainty or often address it by computing probability distributions of other traffic participants over time. Probabilistic approaches make it possible to predict the collision probability with other traffic participants, but cannot formally guarantee (i.e. cannot mathematically prove for given assumptions) whether a planned maneuver is collision-free. Our approach addresses exactly this problem: instead of computing probability distributions, we compute an over-approximation of all possible occupancies of surrounding traffic participants over time. This makes it possible to prove whether an automated vehicle can possibly collide with other traffic participants. The presented algorithm for occupancy prediction works on arbitrary road networks and produces results within a fraction of the prediction horizon. Experiments based on real-world data validate our approach and show that we could not find a behavior of a traffic participant that is not enclosed in our prediction.

Section: Introductionmentioning

confidence: 99%

Set-Based Prediction of Traffic Participants on Arbitrary Road Networks

IEEE Trans. Intell. Veh.

Magdici

2016

“…If for a traffic scenario, the reachable positions of the ego vehicle do not intersect the reachable positions of another vehicle, these vehicles cannot crash. Reachable sets for vehicles have been investigated in [27], [31]. It has been shown that planned paths of autonomous vehicles are too often evaluated as unsafe by this method, because the reachable sets of other vehicles rapidly cover all positions the autonomous vehicle could possibly move to.…”

mentioning

confidence: 99%

Model-Based Probabilistic Collision Detection in Autonomous Driving

IEEE Trans. Intell. Transport. Syst.

Stursberg

Buss

2009

270

174

Abstract-Safety of planned paths of autonomous cars with respect to the movement of other traffic participants is considered. Thereto, the stochastic occupancy of the road by other vehicles is predicted. The prediction considers uncertainties originating from the measurements and the possible behaviors of other traffic participants. In addition, the interaction of traffic participants as well as the limitation of driving maneuvers due to the road geometry is considered. The result of the presented approach is the probability of a crash for a specific trajectory of the autonomous car. The presented approach is efficient as most intensive computations are performed offline, resulting in a lean online algorithm for real-time application.

“…The differential equations of the vehicle dynamics are given in (1), where the equations forẋ 1 andẋ 3 describe the bicycle model for constant velocity. The orientation angle x 2 is obtained by integration of the yaw rate x 3 and the velocity x 4 by integration of the longitudinal acceleration a x , see (1).…”

Section: A Vehicle Modelmentioning

confidence: 99%

“…The orientation angle x 2 is obtained by integration of the yaw rate x 3 and the velocity x 4 by integration of the longitudinal acceleration a x , see (1). Finally, the velocity and the direction of the center of mass (x 1 + x 2 ) are used to geometrically obtain the position coordinates x 5 and x 6 .…”

Section: A Vehicle Modelmentioning

confidence: 99%

“…Unlike this work, most previous work considers simple dynamic models. A frequently used model is to bound the acceleration in the 2-dimensional plane such that the set of positions is obtained from a double integration resulting in reachable circles [1], [2]. Reachability analysis of slightly Matthias Althoff is with Faculty of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA, email:…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Set-based computation of vehicle behaviors for the online verification of autonomous vehicles

2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC)

Dolan

2011

Abstract-We compute the set of all possible behaviors of an autonomous vehicle using reachability analysis. A reachable set is the set of states a system can possibly reach for a given set of initial states, disturbances, and sensor noise values. We consider autonomous vehicles which plan trajectories for a certain lookahead horizon which are followed using feedback control. While a perfectly followed trajectory might not violate specified safety properties (e.g. lane departures or vehicle collisions), there might exist a violating deviation from the planned trajectory. Given the mathematical model of the controlled vehicle and bounds on uncertainty, our approach detects any possible violation. In addition, the approach provides results faster than real time such that maneuvers of vehicles can be checked before they are fully executed.