Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing robot plan online adjustment. A method includes receiving an initial plan for performing a particular task with a robot having a sensor. The initial plan defines an initial path having a plurality of waypoints. Each waypoint is associated with a target position and a target velocity. The method includes generating an alternative path from the initial path. Generating an alternative path includes generating a plurality of alternative paths including performing respective modifications to one or more waypoints in the initial plan, evaluating each alternative path according to a simulated total time duration required for the robot to traverse the alternative path, and selecting an alternative path having a total time duration that is less than a total time duration of the initial plan.

An automatic truck unloading apparatus and method are provided. The automatic truck unloading apparatus generates sensing information regarding the presence or absence of a pallet on the truck by implementing sensors installed in a region of a truck and a region of a storage area, and sets optimal transport paths for multiple unmanned forklift vehicles based on the sensing information, and unloads a pallet from the truck and moves and stores the pallet in the storage area by implementing an unmanned forklift vehicle.

An exemplary multi-robot system can include, for example, a first robot(s), which can include a communication arrangement and a sensor arrangement configured to detect a presence of an object(s) within a predetermined distance from the first robot(s), and determine a distance from the first robot(s) to the object(s), where the first robot(s) can broadcast a query to the object(s) using the communication arrangement, identify the object(s) as a second robot(s) or a non-robot based on a response received from the object(s). The sensor arrangement can be a Light Detection and Ranging (LiDAR) sensor arrangement. The LiDAR sensor arrangement can be a two-dimensional LiDAR sensor arrangement.

A method for correcting a travelling trajectory of a vehicle which is executed by a processor includes: generating a subject vehicle travelling route that a subject vehicle travels based on map information stored in a database; calculating a travelling trajectory of the subject vehicle to be a target trajectory when the subject vehicle travels on the subject vehicle travelling route; detecting a position of another vehicle travelling on a lane located in a width direction of the subject vehicle by a sensor provided for the subject vehicle; calculating an offset of a position of the other vehicle in another vehicle lane that the other vehicle travels based on the position of the other vehicle; and correcting the travelling trajectory of the subject vehicle in accordance with the offset.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for scheduling resource-constrained actions. In some implementations, data indicating a set of tasks to be performed by a group of multiple robots is received. A set of candidate plan elements is determined for each task in the set of tasks. A constraint profile for each of the candidate plan elements is generated, where each of the constraint profiles indicates a constraint to be satisfied in order to carry out the corresponding candidate plan element. Plan elements configured to perform each of the tasks in the set of tasks are selected based on the constraint profiles, and assembled into a schedule according to optimization criteria. This schedule can be used to perform tasks, and the schedule may account for variability in timing without failure.

Systems and methods provide assistance to an operator of a material handling vehicle. Provided systems and methods include receiving vehicle condition data at a first material handling vehicle from a second material handling vehicle when the second material handling vehicle is within a predetermined communication range, determining a first predicted vehicle position for the first material handling vehicle based on current vehicle conditions, determining a second predicted vehicle position for the second material handling vehicle based on the received vehicle condition data, and determining if the first predicted vehicle position for the first material handling vehicle overlaps with the second predicted vehicle position for the second material handling vehicle. Upon the determination that the first predicted vehicle position overlaps with the second predicted vehicle position, the operator of the first material handling vehicle is provided an indication.

A control apparatus for an automatic-driving vehicle includes a fall detecting unit and a collision preventing unit. The fall detecting unit detects that a load of the automatic-driving vehicle has fallen onto a road. The collision preventing unit performs a collision prevention process that is a process to prevent another vehicle from colliding with the load when the fall detecting unit detects that the load has fallen onto the road.

Disclosed herein are a method for driving a robot based on an external image, and a robot and a server implementing the same. In the method, and the robot and server implementing the same, drive of a robot is controlled further using external images acquired by camera modules installed outside the robot. To this end, a robot according to an embodiment of the present disclosure includes a communication unit configured to communicate with external camera modules acquiring external images including the robot that is being driven, a drive-information acquiring unit configured to acquire driving related information at the time of driving the robot, a driving unit configured to drive the robot, and a control unit configured to control the driving unit using external information including the external images received from the external camera modules and the driving related information.

Autonomous vehicles may be dynamically directed to rendezvous with autonomous vehicle trains or convoys. Current location and/or route information of the Autonomous Vehicle Train (AVT) may be received by an autonomous vehicle. The autonomous vehicle may compare its current location and/or route information to determine a rendezvous point with the AVT. The autonomous vehicle may route itself to the rendezvous point with the AVT. Once there, the autonomous vehicle may verify the identification of the AVT, such as by using sensors/cameras to verify a lead vehicle of the AVT (e.g., by verifying make/model, color, and/or license plate). The autonomous vehicle and lead vehicle may communicate to allow the autonomous vehicle to join the AVT. A minimum level of autonomous vehicle functionality may be verified prior to the autonomous vehicle being allowed to join the AVT. As a result, vehicle traffic flow and travel experience by passengers may be enhanced.

A server station receives situation information and vehicle information respectively from three vehicles. The server station calculates how to pass by an on-coming vehicle for each of the three vehicles, and sends to each of the three vehicles a wait instruction of where to wait for and pass by the on-coming vehicle or a notification instruction of the on-coming vehicle when there is no place to wait. For example, the server station sends, to a first vehicle, the notification instruction due to having no place to wait, sends, to a second vehicle, a wait instruction to wait at a current position, which is a pass-by place, until the on-coming vehicle passes, and sends, to a third vehicle, a wait instruction to wait in a pass-by place, which is available to the third vehicle.