Motion prediction and motion planning problems are deeply interconnected for urban autonomous driving. In this project, we target the problem of safe, feasible and human-like motion generation. A non-conservatively defensive strategy (NCDS) is proposed, which is defensive under the worst case to guarantee safety, but not conservative so as to degrade driving quality and generate behaviors which...

in this paper using strongly duplexes we introduce a new class of (semi)hypergroups. the associated (semi)hypergroup from a strongly duplex is called duplex (semi)hypergroup. two computer programs written in matlab show that the two groups $z_{2n}$ and $z_{n}times z_{2}$ produce a strongly duplex and its associated hypergroup is a complementary feasible hypergroup.

Motivation: The time-varying imagery captured by a video camera contains a wealth of raw information about the three-dimensional dynamics and structure of the world. Once the camera motion is determined and compensated for, the remaining scene motion may be used to build a global representation of this temporal data. Such tasks as activity detection, 2D mosaic construction, and 3D site modeling...

This paper presents a framework for motion planning with dynamics as hybrid search over the continuous space of feasible motions and the discrete space of a low-dimensional workspace decomposition. Each step of the hybrid search consists of expanding a frontier of regions in the discrete space using cost heuristics as guide followed by sampling-based motion planning to expand a tree of feasible...

This paper describes an original approach for non parametric motion analysis in image sequences. It relies on a statistical modeling of distributions of local motion-related measurements, computed over image sequences, resulting from spatio-temporal random walks. It handles in a single probabilistic framework both spatial and temporal properties of motion content. The important feature of our m...

Multiple cues play a crucial role in image interpretation. A vision system that combines shape, colour, motion, prior scene knowledge and object motion behaviour is described. We show that the use of interpretation strategies which depend on the image data, temporal context and visual goals significantly simplifies the complexity of the image interpretation problem and makes it computationally ...

For real-world robotic systems, the ability to efficiently obtain motion plans of good quality over a diverse range of problems, is crucial. Large, dense motion-planning roadmaps can typically ensure the existence of such good quality solutions for most problems. This thesis proposes an algorithmic framework for anytime planning on large, dense motion-planning roadmaps. The size of the roadmap ...

Although one of the fundamental problems in robotics, the motion planning problem is inherently hard from a computational point of view. In particular, the piano movers’ problem [1], [2] is known to be PSPACE-hard, which implies that any algorithm aimed to solve this problem (with completeness guarantees) is expected not to scale well with increasing number of dimensions of the configuration sp...