Autonomous mobile robots include transfer systems that may receive multiple items for delivery to one or more destinations. The transfer systems may be specifically configured to detect and identify items that are placed on loading surfaces, and to independently discharge specific items at selected destinations or to selected recipients. The transfer systems feature loading surfaces that may be defined by a plurality of independently operable conveyors to receive or discharge items, by independently operable floors that allow items to pass therethrough, or by independently operable diverters for detecting and expelling items therefrom. The transfer systems may receive items from, or discharge items to, one or more humans, other robots, or other systems such as conveyors, chutes, robotic arms or other mechanical implements or effectors, and be aligned at any angle or provided at any height, as desired.

An autonomous electric vehicle comprises a battery electrically connected to the electric motor for powering the electric motor and a battery status prediction module to predict, based on event data from a mobile device of a user of the vehicle, whether the vehicle will be parked at a destination and a time period when the vehicle will be parked. The battery status prediction module predicts a predicted battery status at the end of the time period based on a temperature profile for the time period obtained from a remote weather server. The battery status prediction module determines if the predicted battery status at the end of the time period will have at least a minimum battery capacity to travel a distance to a charging station determined by the battery status prediction module from the destination and a location of the charging station.

The invention relates to method of operating a fleet of autonomous vehicles at a work site having a loading area at which a loading device is provided for loading material onto said autonomous vehicles. The method includes controlling a first vehicle to drive in a first driving mode until it reaches a start position of the loading area, deactivating the first driving mode by controlling the first vehicle to be positioned in the loading area in a second driving mode, controlling a second vehicle to come into contact with and to push the first vehicle along the loading area and past the loading device for loading material onto the first vehicle as the first vehicle passes by the loading device, and reactivating the first driving mode of the first vehicle when the second vehicle has pushed the first vehicle to an end position of the loading area.

A remotely operated vehicle includes an arrangement to provide a pre-alert and tracking of a position of the vehicle following a travelling route relative to tracks laid out on rails in x-, y-directions on a rail system. The vehicle has first and seconds sets of wheels connected to drives for moving the vehicle in corresponding x-, y-directions on the rail system. The arrangement includes at least one sensor module provided with at least four sensors. A first sensor is directed vertically downwards to detect the rails in the x-direction on the sensor module. A second sensor is directed vertically downwards to detect the rails in the y-direction on the sensor module. A third sensor is positioned on the sensor module to detect a corner of an intersection between the rails in the x-direction and y-direction. A fourth sensor is configured to detect a remaining distance to the arrival of the vehicle at a set position, by detecting the rails in the x direction when travelling in the y direction, and detecting the rail in the y direction when travelling in the x direction. The fourth sensor is placed at a predefined position on the sensor module. A controller is provided on the vehicle to receive the output from at least one of the sensors and to pre-alert the remaining distance of the arrival of the vehicle at the position.

A vehicle coordination system is provided for coordinating the trajectories of vehicles on a road network. The vehicle coordination system comprises a plurality of vehicles each having respective vehicle position tracking assemblies that are in communication with respective vehicle communication systems for transmitting vehicle state messages including positions of the vehicles. A task assignment allocator is provided that is arranged to generate task assignments for each of the plurality of vehicles, including destinations in the road network for the vehicles. A vehicle coordination assembly is in communication with the vehicle communication systems via a data network for receiving the vehicle state messages. The vehicle coordination assembly is configured to determine respective paths for each vehicle to arrive at their respective destinations and determine trajectory control commands for each vehicle to traverse their respective paths whilst optimizing a predetermined objective and avoiding active interactions of two or more of the vehicles occurring in any shared areas of the paths. The vehicle coordination assembly is configured to transmit the trajectory control commands to each vehicle. The predetermined objective may be an aggregate traversal time for the vehicles.

A robotic cleaner may include a body, one or more driven wheels configured to urge the body across a surface to be cleaned, one or more distance sensors disposed at least partially within the body such that the one or more distance sensors face the surface to be cleaned and a processor. The one or more distance sensors may be configured to output a measure of a detection distance that extends in a direction of the surface to be cleaned. The processor may be configured to determine whether an abnormality has been detected based, at least in part, on the measure of the detection distance and may be configured to determine a first velocity estimate based, at least in part, on the detection of the abnormality.

Systems and methods for robotic path planning are disclosed. In some implementations of the present disclosure, a robot can generate a cost map associated with an environment of the robot. The cost map can comprise a plurality of pixels each corresponding to a location in the environment, where each pixel can have an associated cost. The robot can further generate a plurality of masks having projected path portions for the travel of the robot within the environment, where each mask comprises a plurality of mask pixels that correspond to locations in the environment. The robot can then determine a mask cost associated with each mask based at least in part on the cost map and select a mask based at least in part on the mask cost. Based on the projected path portions within the selected mask, the robot can navigate a space.

A method of controlling a vehicle or robot. The method includes the following steps: determining a first control sequence, determining a second control sequence for controlling the vehicle or robot depending on the first control sequence, a current state of the vehicle or robot, and on a model characterizing a dynamic behavior of the vehicle or robot, controlling the vehicle or robot depending on the second control sequence, wherein the determining of the first control sequence is performed depending on a first candidate control sequence and a second candidate control sequence.

Methods and apparatus for making autonomous vehicle handover decisions are described. A handover decision involves deciding if an autonomous vehicle should be handed off from one worker to another worker. The methods allow for decisions to be made in real or near real time shortly before an autonomous vehicle changes location. Worker time, if a handover is not implemented, is considered including the amount of worker time involved with the worker moving with the autonomous vehicle to the new location as compared to a new worker meeting the autonomous vehicle at the new location or on the way to the new location. Handover decisions can consider worker distribution and/or order priority. Such factors can be used to weight one or more time based cost values with a cost value representation of the cost if a handover is not implemented vs implementing a handover being compared to make the handover decision.

A cleaning method of a cleaning robot, a chip, and a cleaning robot. The cleaning method of the cleaning robot includes: moving forward and along a first lateral direction to form a first cleaning path; moving backward to form a second cleaning path; moving forward and along a second lateral direction to form a third cleaning path, where the second lateral direction is opposite to the first lateral direction; and repeatedly performing the first cleaning path, the second cleaning path, and the third cleaning path in turn. The cleaning method of the cleaning robot improves the cleaning effect by repeatedly performing a three-segment series of paths.