The article deals with the analysis and interpretation of dynamic scenes typical of urban driving. The key objective is to assess risks of collision for the ego-vehicle. We describe our concept and methods, which we have integrated and tested on our experimental platform on a Lexus car and a driving simulator. The on-board sensors deliver visual, telemetric and inertial data for environment monitoring. The sensor fusion uses our Bayesian Occupancy Filter for a spatio-temporal grid representation of the traffic scene. The underlying probabilistic approach is capable of dealing with uncertainties when modeling the environment as well as detecting and tracking dynamic objects. The collision risks are estimated as stochastic variables and are predicted for a short period ahead with the use of Hidden Markov Models and Gaussian processes. The software implementation takes advantage of our methods, which allow for parallel computation. Our tests have proven the relevance and feasibility of our approach for improving the safety of car driving.

Practical aspects of motion generation and control f o r parking a nonholonomic autonomous vehicle are considered. A n iterative algorithm for the parallel parking maneuver is proposed. It is based on ultrasonic range data processing. To co:ntrol the steering angle and longitudinal velocity of the vehicle during the parking maneuver, sinusoidal reference functions are used. To prevent collisions, the maneuver is car-I-rccl out as a reactive motion. The developzd control is experzmentally verified for a LIGIER ekctric auLonomous vehicle.

No abstract

No abstract

Path generation, execution and motion control for an omnidirectional mobile robot (vehicle) are considered. Real-time path generation is based on the polynomial spline-interpolation with prediction of velocities of a spline-function. The mobile vehicle control is performed with the use of its kinematic model and digital PIDcontrollers of the wheels. The theoretical approach is illustrated by the obtained experimental results.

No abstract

This video illustrates a control approach developed to perform parallel parking and returning to traffic maneuvers for a car capable of autonomous motion. The key idea is t o carry out a motion control procedure involving a "Localization-Planning-Execution" cycle until a specified location of the car relative to its environment is reached. Range measurements are used to model environmental objects around the car. The automatic maneuvers developed are demonstrated o n an experimental electric autonomous car in a usual traffic environment.

No abstract