Abstract:
An autonomous mobile robot includes a chassis, a drive supporting the chassis above a floor surface in a home and configured to move the chassis across the floor surface, a variable height member being coupled to the chassis and being vertically extendible, a camera supported by the variable height member, and a controller. The controller is configured to operate the drive to navigate the robot to locations within the home and to adjust a height of the variable height member upon reaching a first of the locations. The controller is also configured to, while the variable height member is at the adjusted height, operate the camera to capture digital imagery of the home at the first of the locations.
Abstract:
The present teachings provide a method of controlling a remote vehicle having an end effector and an image sensing device. The method includes obtaining an image of an object with the image sensing device, determining a ray from a focal point of the image to the object based on the obtained image, positioning the end effector of the remote vehicle to align with the determined ray, and moving the end effector along the determined ray to approach the object.
Abstract:
A system increases an operator's situational awareness while the operator controls a remote vehicle. The system comprises an operator control unit having a point-and-click interface configured to allow the operator to view an environment surrounding the remote vehicle and control the remote vehicle, and a payload attached to the remote vehicle and in communication with at least one of the remote vehicle and the operator control unit. The payload comprises an integrated sensor suite including GPS, an inertial measurement unit, a stereo vision camera, and a range sensor, and a computational module receiving data from the GPS, the inertial measurement unit, the stereo vision camera, and the range sensor and providing data to a CPU including at least one of an autonomous behavior and a semi-autonomous behavior that utilize data from the integrated sensor suite.
Abstract:
The present invention is a robotic mobile platform vehicle that can be thrown into hostile or hazardous environments for gathering information and transmitting that information to a remotely located control station and a system comprising the robotic mobile platform. One of the key features of the invention is that at least four imaging assemblies are mounted on the robotic platform and that the system has the processing ability to stitch the views taken by the four imaging devices together into an omni-directional image. Another feature is that the user can steer the robotic platform simply by touching an object in one of the images displayed in the graphic interface. The robotic platform can then either point its sensors towards that object or, if so instructed, compute the direction to the object and travel to it without any further input from the user
Abstract:
A robotic apparatus for use in construction that is capable of traversing a selected area autonomously. The robotic apparatus is provided in two models, a master that can record directive and "environmental signal" readings, or that can record received location information, to provide at least one command recorded on a machine-readable medium representing an instruction for traversing an area of interest, and a slave that lacks the recording capability. Both master and slave models can replay recorded commands, and compare the expected orientation from the command with an actual orientation sensed during autonomous operation. If an error exceeding a predetermined value is observed, a corrective action is taken. The robotic apparatus is to perform a task, such as marking locations in construction of a building for installation of services such as wiring and plumbing.
Abstract:
A system and method for controlling a remote vehicle (2) comprises a hand-held controller (4) including a laser generator (5) for generating a laser beam (6). The hand-held controller (4) is manipulate to aim and actuate the laser beam to designate a destination for the remote vehicle (2). The remote vehicle senses a reflection of the laser beam and moves toward the designated destination. The hand-held controller allows single-handed control of the remote vehicle and one or more of its payloads. A method for controlling a remote vehicle (2) via a laser beam (6) comprises encoding control signals for a remote vehicle into a laser beam that is aimed and sent to a designated destination for the remote vehicle, and sensing a reflection of the laser beam, decoding the control signals for the remote vehicle, and moving toward the designated destination.
Abstract:
An arrangement for obstacle detection in autonomous vehicles wherein two significant data manipulations are employed in order to provide a more accurate read of potential obstacles and thus contribute to more efficient and effective operation of an autonomous vehicle. A first data manipulation involves distinguishing between those potential obstacles that are surrounded by significant background scatter in a radar diagram and those that are not, wherein the latter are more likely to represent binary obstacles that are to be avoided. A second data manipulation involves updating a radar image to the extent possible as an object comes into closer range. Preferably, the first aforementioned data manipulation may be performed via context filtering, while the second aforementioned data manipulation may be performed via blob-based hysteresis.
Abstract:
A mobile vehicle navigation system includes a polygon rasterization module configured to perform a polygon rasterization process on one or more maps of an obstacle field to identify obstacle-free regions within the obstacle field. The navigation system further includes a shortest path module configured to select an optimal trajectory along which the mobile vehicle can safely traverse the obstacle field and a control module configured to ensure that the mobile vehicle can successfully traverse the optimal trajectory selected by the shortest path module. The navigation system can advantageously generate obstacle-free trajectories through an obstacle field in substantially real time in response to user requests.
Abstract:
A path planner (10) and a method for determining a path for a vehicle comprises defining a starting point for the vehicle. A termination point is defined. An obstacle detector (14) detects one or more obstacles in a work area between the starting point and the termination point. A boundary zone is defined about each corresponding obstacle. Candidate paths are identified between the starting point and the termination point. Each candidate path only intersects each boundary zone once for each corresponding obstacle. An economic cost is estimated for traversing each candidate path or a portion thereof between the starting point and the termination point. A preferential path is selected from the identified candidate paths based on the preferential path being associated with a lowest estimated economic cost.
Abstract:
A method and apparatus for computing properties of a physical environment is provided, using a plurality of agents forming a distributed network embedded within the environment. The method comprises determining an initiating agent (200), transmitting a signal including a cumulative cost value to neighboring agents (202), and processing the signal at each neighboring agent to augment the cumulative cost value with local information (204). If multiple signals are received, determining which has the best cumulative cost value for generating a new signal (206), then treating the neighboring agent as an initiating agent (208) and transmitting the new signal to neighboring agents (208) and retaining the best augmented cost value in memory (210). Methods further include determining paths using shortest path computations, using dual gradients for aligning agents on a path between two reference agents, and discovering and converging agents on choke points.