Detection, prediction, and avoidance of dynamic obstacles in urban environments

Abstract

Abstract-We present an approach for robust detection, prediction, and avoidance of dynamic obstacles in urban environments. After detecting a dynamic obstacle, our approach exploits structure in the environment where possible to generate a set of likely hypotheses for the future behavior of the obstacle and efficiently incorporates these hypotheses into the planning process to produce safe actions. The techniques presented are very general and can be used with a wide range of sensors and planning algorithms. We present results from an implementation on an autonomous passenger vehicle that has traveled thousands of miles in populated urban environments and won first place in the DARPA Urban Challenge.

Why did the robot cross the road? — Learning from multi-modal sensor data for autonomous road crossing

“…Such approaches aim to compute the possible paths that an agent might follow starting from its current state [5,10,11]. Meissner et al use a multi-sensor tracking system for classification of relevant objects [16].…”

Pervasive Crowd Mapping for Dynamic Environments

“…Multi-sensory technology and data fusion is used in autonomous driving [9], [10] to extract information about the surrounding environment and provide guidance. Data mining techniques [11], [12], hierarchical Markov decision processes [13] and neural networks [14], [15] are also often used for this purpose.…”

“…Multisensory approaches are also used to provide orientation and mobility to the blind [3], [4], addressing user location, navigation and environment recognition problems in a integrated solution [5]- [8]. The multi-sensory technology and data fusion is used in other contexts for the same purpose, as for instance in autonomous driving [9], [10]. Are often used data mining techniques [11], [12], hierarchical Markov decision processes [13] and neural networks [14], [15] for information extraction from the data gathered.…”

Bayesian environment representation, prediction, and criticality assessment for driver assistance systems

“…• Methods that fuse dynamic motion models with behavior and environment descriptions [5,45,75,82,88,144,211,236].…”