Abstract: Described herein are embodiments of a method and system that uses a vertical or upward facing imaging sensor to compute vehicle attitude, orientation, or heading and combines the computed vehicle attitude, orientation, or heading with range bearing measurements from an imaging sensor, LiDAR, sonar, etc., to features in the vicinity of the vehicle to compute accurate position and map estimates.

Abstract: A system for controlling a vehicle comprising a vehicle condition monitor coupled to the vehicle and configured to generate a plurality of vehicle operational data signals and a predictive behavior system coupled to the vehicle condition monitor and configured to generate vehicle control data as a function of the vehicle operational data signals and operator historical data.

Abstract: A system comprising a sensor, a protective enclosure configured to enclose the sensor, a mounting pad configured to be attached to a location of a vehicle, the mounting pad having a contact area as a function of a weight of the sensor and the protective enclosure, a processor coupled to the sensor, the processor configured to associate the sensor with the location of the vehicle and wherein the sensor and the protective enclosure are attached to the mounting pad, and the mounting pad is attached to the surface of the vehicle using an adhesive layer.

Abstract: A system comprising a sensor, a protective enclosure configured to enclose the sensor and a mounting pad configured to be attached to a predetermined surface of a predetermined vehicle, the mounting pad having a predetermined contact area as a function of a weight of the sensor and the protective enclosure. The sensor and the protective enclosure are attached to the mounting pad, and the mounting pad is attached to the predetermined surface of the vehicle using an adhesive layer that extends over the predetermined contact area that is selected to provide a maximum weight support that is correlated to a weight of the sensor and the protective enclosure.

Abstract: A system for automated driver assistance, comprising a plurality of sensors configured to generate sensor data, a vehicle controller configured to generate vehicle speed data, vehicle braking data, vehicle control commands and vehicle braking commands and a processor operating under algorithmic control and configured to receive the sensor data and the vehicle speed data, to process the sensor data and the vehicle speed data to generate control data, and to transmit the control data to the vehicle controller to cause the vehicle controller to generate the vehicle speed commands and the vehicle braking commands.

Abstract: A method of visual navigation for a robot includes integrating a depth map with localization information to generate a three-dimensional (3D) map. The method also includes motion planning based on the 3D map, the localization information, and/or a user input. The motion planning overrides the user input when a trajectory and/or a velocity, received via the user input, is predicted to cause a collision.

Abstract: A system comprising a first connector configured to be coupled to an assembly having a plurality of electrical signal outputs from user controls of a vehicle. A second connector configured to be coupled to an assembly providing a plurality of inputs to a plurality of vehicle control systems. An interface device configured to process the plurality of electrical signal outputs from user controls of the vehicle and to modify the plurality of electrical signal outputs to generate the plurality of inputs to the plurality of vehicle control systems.

Abstract: A system comprising a sensor, a protective enclosure configured to enclose the sensor and a mounting pad configured to be attached to a predetermined surface of a predetermined vehicle, the mounting pad having a predetermined contact area as a function of a weight of the sensor and the protective enclosure. The sensor and the protective enclosure are attached to the mounting pad, and the mounting pad is attached to the predetermined surface of the vehicle using an adhesive layer that extends over the predetermined contact area that is selected to provide a maximum weight support that is correlated to a weight of the sensor and the protective enclosure.

Abstract: A method for defining a sensor model includes determining a probability of obtaining a measurement from multiple potential causes in a field of view of a sensor modeled based on a stochastic map. The stochastic map includes a mean occupancy level for each voxel in the stochastic map and a variance of the mean occupancy level for each pixel. The method also includes determining a probability of obtaining an image based on the determined probability of obtaining the measurement. The method further includes planning an action for a robot, comprising the sensor, based on the probability of obtaining the image.

Abstract: Described herein are embodiments of a method and system that uses a vertical or upward facing imaging sensor to compute vehicle attitude, orientation, or heading and combines the computed vehicle attitude, orientation, or heading with range bearing measurements from an imaging sensor, LiDAR, sonar, etc., to features in the vicinity of the vehicle to compute accurate position and map estimates.

Abstract: A method for controlling a vehicle, comprising generating image data at a camera system of a robotic vehicle, receiving the image data at a processor of the robotic vehicle, identifying a plurality of bright spots in the image data using the processor, computing a boundary for the plurality of bright spots and generating control data as a function of the boundary.

Abstract: A method to retrofit industrial lift trucks for automated material handling, comprising configuring a processor to associate a plurality of sensors with a plurality of locations of a vehicle. Implementing a mapping mode of the processor to cause the plurality of sensors to generate sensor data as the vehicle is moved around a facility. Generating a map of the facility from the sensor data, and receiving an operator input to define a mission, wherein the operator input comprises one of an object pick up command and an object drop off command. Following pick-up and drop-off commands as defined in a mission to move pallets and following a human in an autonomous fashion using a combination of sensors.

Abstract: Material handling vehicles also known as lift trucks, e.g., forklifts, pallet jacks, reach trucks etc., are an essential component of any supply chain and logistics operation. These vehicles are typically driven by human operators and are used to move goods inside factories, warehouses etc. We develop a system and method to retrofit manual lift trucks with a supplemental control system (retrofit kit) that includes sensors, communication devices, computers, electrical circuits and mechanical actuators such that a lift truck can carry out material handling tasks autonomously without the presence of a human operator. The retrofit also allows the lift truck to be controlled remotely by a human tele-operator and can transmit and receive data from a remote computer.

Abstract: A method substantially simultaneously plans a path and maps an environment by a robot. The method determines a mean of an occupancy level for a location in a map. The method also includes determining a probability distribution function (PDF) of the occupancy level. The method further includes calculating a cost function based on the PDF. Finally, the method includes simultaneously planning the path and mapping the environment based on the cost function.

Abstract: A method of visual navigation for a robot includes integrating a depth map with localization information to generate a three-dimensional (3D) map. The method also includes motion planning based on the 3D map, the localization information, and/or a user input. The motion planning overrides the user input when a trajectory and/or a velocity, received via the user input, is predicted to cause a collision.

Abstract: A method of motion planning for an agent to reach a target includes determining a frontier region between a frontier at a current time and a frontier at a next time. Waypoints are sampled in the frontier region with a bias toward the target. A path to reach the target is selected based on a sequence of the sampled waypoints.

Abstract: A method for defining a sensor model includes determining a probability of obtaining a measurement from multiple potential causes in a field of view of a sensor modeled based on a stochastic map. The stochastic map includes a mean occupancy level for each voxel in the stochastic map and a variance of the mean occupancy level for each pixel. The method also includes determining a probability of obtaining an image based on the determined probability of obtaining the measurement. The method further includes planning an action for a robot, comprising the sensor, based on the probability of obtaining the image.

Abstract: A method substantially simultaneously plans a path and maps an environment by a robot. The method determines a mean of an occupancy level for a location in a map. The method also includes determining a probability distribution function (PDF) of the occupancy level. The method further includes calculating a cost function based on the PDF. Finally, the method includes simultaneously planning the path and mapping the environment based on the cost function.

Abstract: A method for generating a map includes determining an occupancy level of each of multiple voxels. The method also includes determining a probability distribution function (PDF) of the occupancy level of each voxel. The method further includes performing an incremental Bayesian update on the PDF to generate the map based on a measurement performed after determining the PDF.

Abstract: A method of calculating a most likely map based on batch data includes gathering a corpus of sensor measurements indexed by a location of a sensor throughout an environment to be mapped. The method also includes determining, after gathering the corpus of sensor measurements, a most likely occupancy level of each voxel of multiple voxels of the environment in accordance with the corpus of sensor measurements and a stochastic sensor model. The method further includes calculating the most likely map based on the determined most likely occupancy level.