A Generic Concept of a System for Predicting Driving Behaviors

Bonnin, Sarah; Kummert, Franz; Schmudderich, Jens

doi:10.1109/itsc.2012.6338695

Cited by 21 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [9], a system is presented which recognizes the class of the situation a traffic participant is facing, based on a manually constructed decision tree. A situation specific classifier is then used to predict the behavior type of a traffic participant.…”

Section: State-of-the-artmentioning

confidence: 99%

Learning Driver Behavior Models from Traffic Observations for Decision Making and Planning

Gindele

Brechtel

Dillmann

2015

IEEE Intell. Transport. Syst. Mag.

182

View full text Add to dashboard Cite

Estimating and predicting traffic situations over time is an essential capability for sophisticated driver assistance systems and autonomous driving. When longer prediction horizons are needed, e.g., in decision making or motion planning, the uncertainty induced by incomplete environment perception and stochastic situation development over time cannot be neglected without sacrificing robustness and safety. Building consistent probabilistic models of drivers interactions with the environment, the road network and other traffic participants poses a complex problem. In this paper, we model the decision making process of drivers by building a hierarchical Dynamic Bayesian Model that describes physical relationships as well as the driver's behaviors and plans. This way, the uncertainties in the process on all abstraction levels can be handled in a mathematically consistent way. As drivers behaviors are difficult to model, we present an approach for learning continuous, non-linear, context-dependent models for the behavior of traffic participants. We propose an Expectation Maximization (EM) approach for learning the models integrated in the DBN from unlabeled observations. Experi-ments show a significant improvement in estimation and prediction accuracy over standard models which only consider vehicle dynamics. Finally, a novel approach to tactical decision making for autonomous driving is outlined. It is based on a continuous Partially Observable Markov Decision Process (POMDP) that uses the presented model for prediction.

show abstract

Section: State-of-the-artmentioning

confidence: 99%

Learning Driver Behavior Models from Traffic Observations for Decision Making and Planning

Gindele

Brechtel

Dillmann

2015

IEEE Intell. Transport. Syst. Mag.

182

View full text Add to dashboard Cite

show abstract

“…Probabilistic models like costmaps (Bahram et al, 2016) account for physical constraints on the movements of the other vehicles. Classification approaches categorize and represent scenes in a hierarchy (Bonnin et al, 2012) based on the most generic ones to predict behavior for a variety of different situations.…”

Section: Introductionmentioning

confidence: 99%

An Investigation of Vehicle Behavior Prediction Using a Vector Power Representation to Encode Spatial Positions of Multiple Objects and Neural Networks

Mirus

Blouw²,

Stewart³

et al. 2019

Front. Neurorobot.

View full text Add to dashboard Cite

Predicting future behavior and positions of other traffic participants from observations is a key problem that needs to be solved by human drivers and automated vehicles alike to safely navigate their environment and to reach their desired goal. In this paper, we expand on previous work on an automotive environment model based on vector symbolic architectures (VSAs). We investigate a vector-representation to encapsulate spatial information of multiple objects based on a convolutive power encoding. Assuming that future positions of vehicles are influenced not only by their own past positions and dynamics (e.g., velocity and acceleration) but also by the behavior of the other traffic participants in the vehicle's surroundings, our motivation is 3-fold: we hypothesize that our structured vector-representation will be able to capture these relations and mutual influence between multiple traffic participants. Furthermore, the dimension of the encoding vectors remains fixed while being independent of the number of other vehicles encoded in addition to the target vehicle. Finally, a VSA-based encoding allows us to combine symbol-like processing with the advantages of neural network learning. In this work, we use our vector representation as input for a long short-term memory (LSTM) network for sequence to sequence prediction of vehicle positions. In an extensive evaluation, we compare this approach to other LSTM-based benchmark systems using alternative data encoding schemes, simple feed-forward neural networks as well as a simple linear prediction model for reference. We analyze advantages and drawbacks of the presented methods and identify specific driving situations where our approach performs best. We use characteristics specifying such situations as a foundation for an online-learning mixture-of-experts prototype, which chooses at run time between several available predictors depending on the current driving situation to achieve the best possible forecast.

show abstract

“…Predictions of behavior patterns (such as lane change, left turn, etc.) are described in [14], [15]. Due to the importance of the prediction of lane changes, much work has focused on this problem [16]- [19].…”

Section: Introductionmentioning

confidence: 99%

Road occupancy prediction of traffic participants

Althoff

Hess

Gambert

2013

16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013)

View full text Add to dashboard Cite

We predict the road occupancy of traffic participants for collision avoidance systems. The occupancy sets are computed for consecutive time intervals and contain all reachable positions of traffic participants in compliance with a proposed dynamic model. Those sets make it possible to check if planned emergency maneuvers are collision-free in all possible future scenarios. However, no algorithm exists for exactly computing the occupancy when the model forbids unrealistic behavior such as leaving road boundaries or largely exceeding speed limits. For this reason, we provide methods to tightly overapproximate occupancy sets to ensure safe emergency maneuvers. We demonstrate the applicability of the approach by numerical examples, which show that the occupancy computation is not only efficient, but also tight enough to trigger emergency maneuvers almost at the last possible point in time.

show abstract

A Generic Concept of a System for Predicting Driving Behaviors

Cited by 21 publications

References 12 publications

Learning Driver Behavior Models from Traffic Observations for Decision Making and Planning

Learning Driver Behavior Models from Traffic Observations for Decision Making and Planning

An Investigation of Vehicle Behavior Prediction Using a Vector Power Representation to Encode Spatial Positions of Multiple Objects and Neural Networks

Road occupancy prediction of traffic participants

Contact Info

Product

Resources

About