Locus Robotics Corporation

Other

Thomas Moore

Bradley Powers

Michael Sussman

Hian Kai Kwa

Sean Johnson

Michael Charles Johnson

Christina Nicole Fong

Aron Klair Insinga

Matthew Whitaker

A method for predicting a collision between a mobile robot and an obstacle in an environment includes obtaining laser scan data for the mobile robot at a current location in the environment. The method also includes predicting a future location of the mobile robot in the environment and producing predicted laser scan data corresponding to the future location of the mobile robot in the environment. The method further includes assessing the predicted laser scan data relative to the mobile robot at the current location to determine whether a collision with an obstacle is predicted.

Robot obstacle collision prediction and avoidance

Systems and methods for contextually mapping zones within a space for regulating robotic navigation within the space include defining, by at least one fiducial marker positioned within the space, a zone within the space, associating a rule with the zone, the rule at least partially dictating operation of one or more robots within the zone, and operating the one or more robots within the zone consistent with the rule.

Zone engine for providing context-augmented map layer

A method and system for docking a robot with a charger docking station, including receiving an initial pose and receiving a mating pose associated with the robot charger docking station, performing a first navigation from a location to the initial pose, and performing a second navigation of the robot from the initial pose to the mating pose. The second navigation may proceed substantially along an arc path from the initial pose to the mating pose, thereby, upon arriving at the mating pose, an electrical charging port of the robot mates with an electrical charging assembly. The arc path may be associated with a section of a unique circle having a radius and a center equidistant from the initial pose and the mating pose. Controlling for error may include a proportional control and/or weighted control or switching between the controls to maintain an error below a threshold.

Robot charger docking control

A method and system for navigation of a robot along a goal path and avoiding obstacles. The method includes receiving goal pose for one or more robots and determining a goal path for a first robot while avoiding moving and fixed obstacles of a received obstacle map. A first objective function is evaluated to select a preferred velocity from a generated set of candidate velocities, the selecting based on one or more weighted cost functions. A set of velocity obstacles created based on the poses of the one or more robots and the preferred velocity is used in evaluating a second objective function to determine the motion of the robot in the next time cycle. Creating the set of velocity objects includes converting the preferred velocity from a non-holonomic to a holonomic velocity.

Dynamic window approach using optimal reciprocal collision avoidance cost-critic

An electrical charging station for charging an autonomous robot with first and second cameras used for docking the autonomous robot with the electrical charging station. There is a front side cover with a surface, the front side cover including a first charging member configured to receive a second charging member on the autonomous robot when the autonomous robot is docked with the charging station for charging. There is a first fiducial surface including a first fiducial marker affixed to the first surface. The first fiducial surface defines a plane disposed at a first non-zero angle relative to a plane defined by the surface of the front side cover. There is a second fiducial surface including a second fiducial marker affixed to the second surface. The second fiducial surface defines a plane disposed at a second non-zero angle relative to the plane defined by the surface of the front side cover.

Autonomous robot charging station

A method for navigating a robot from a current pose to a goal pose. A map represents obstacles and free space within an area for robot navigation. A matching map pyramid and an exclusion map pyramid are constructed based on the map and decimations from a highest resolution to successively lower resolutions of the map pyramids. Current pose for navigating from a current location to a goal pose along a goal path includes determining a search area and creating a search heap. Scoring of search tasks on the search heap determines a best candidate pose at a highest resolution matching map, or expands the search heap with search tasks at the next higher resolution matching map. Expanding the search heap at the next higher resolution matching map avoids search tasks that would localize the robot in an exclusion zone.

Multi-resolution scan matching with exclusion zones

A method, system, and wheeled base for navigating a robot for docking with a charger docking station. The robot receives an initial pose associated with a robot charger docking station and a mating pose associated with the robot charger docking station. The robot first navigates from a location to an initial pose using scan matching to a first map. The robot performs a second navigation from the initial pose to the mating pose using scan matching to a second map, thereby causing an electrical charging port of the robot to mate with an electrical charging assembly of the robot charger docking station. Localization during charger docking may use a higher resolution map than when navigating to the docking station. Localizing against the robot charger docking station may be performed on a higher resolution map of the docking station alone.

Growing community of inventors

Edinburgh, United Kingdom

Thomas Moore