Five Ai Limited

Alejandro Bordallo Mico

Alexandre Oliveira E Silva

Subramanian Ramamoorthy

Majd Hawasly

Andrew Blake

Francisco Maria Girbal Eiras

Svetlin Valentinov Penkov

Svetlin-Valentinov Penkov

Bence Magyar

Steffen Jaekel

Marco Andrea Ferri

With respect to an adaptive cruise control method for autonomously adapting the speed of an ego vehicle () to maintain a target headway, headway being distance from the ego vehicle to a forward vehicle (), the ego vehicle equipped with a perception system () for measuring a current headway and a current speed and acceleration of the forward vehicle relative to ego vehicle, the method may comprise: in response to detecting that the current headway is below the target headway, determining and implementing a deceleration strategy for increasing to the target headway; wherein the deceleration strategy is determined so as to selectively optimize for comfort in dependence on a predicted headway, the predicted headway computed for a future time instant based on the current speed and acceleration of the forward vehicle relative to the ego vehicle.

Adaptive cruise control

A computer-implemented method of planning a path for a mobile robot in the presence of a set of obstacles comprises: computing for each obstacle a probabilistic obstacle position distribution; computing at least one path-independent function as a combination of the probabilistic obstacle position distributions; and for at least one candidate path, determining an upper bound on the total probability of obstacle collision along that path, by aggregating the path-independent function based on an area defined by the candidate path and a mobile robot shape, wherein the path-independent function is independent of the candidate path.

Path planning in mobile robots

The invention provides a computer-implemented method of planning a path for a mobile robot such as an autonomous vehicle in the presence of K obstacles. The method uses, for each of the K obstacles, a shape Bk and a density function pk(x) representing the probabilistic position of the obstacle. The method repeats the following steps for at least two different paths A: &#x2014;choosing a path A, where A is the swept area of the robot within a given time interval; and&#x2014;calculating based on the density function of each obstacle and the swept path an upper bound on the total probability of at least one collision Fbetween the robot and the K obstacles. This allows a number of candidate paths to be ranked for safety. By precomputing factors of the computational steps over K obstacles, the computation per path is O(N), and not O(NK). A safety threshold can be used to filter out paths below that threshold. An operating path to control the robot can be selected from the remaining paths, optionally based on other factors such as comfort or efficiency.

Growing community of inventors

Bristol, United Kingdom

Alejandro Bordallo Mico