Abstract: Systems and methods for dynamic route planning m autonomous navigation are disclosed. In some exemplary implementations, a robot can have one or more sensors configured to collect data about an environment including detected points on one or more objects in the environment. The robot can then plan a route in the environment, where the route can comprise one or more route poses. The route poses can include a footprint indicative at least in part of a pose, size, and shape of the robot along the route. Each route pose can have a plurality of points therein. Based on forces exerted on the points of each route pose by other route poses, objects in the environment, and others, each route pose can reposition. Based at least in part on interpolation performed on the route poses (some of which may be repositioned), the robot can dynamically route.

Abstract: Robotic devices may be trained by a user guiding the robot along target action trajectory using an input signal. A robotic device may comprise an adaptive controller configured to generate control signal based on one or more of the user guidance, sensory input, performance measure, and/or other information. Training may comprise a plurality of trials, wherein for a given context the user and the robot's controller may collaborate to develop an association between the context and the target action. Upon developing the association, the adaptive controller may be capable of generating the control signal and/or an action indication prior and/or in lieu of user input. The predictive control functionality attained by the controller may enable autonomous operation of robotic devices obviating a need for continuing user guidance.

Abstract: The safe operation and navigation of robots is an active research topic for many real-world applications, such as the automation of large industrial equipment. This technological field often requires heavy machines with arbitrary shapes to navigate very close to obstacles, a challenging and largely unsolved problem. To address this issue, a new planning architecture is developed that allows wheeled vehicles to navigate safely and without human supervision in cluttered environments. The inventive methods and systems disclosed herein belong to the Model Predictive Control (MPC) family of local planning algorithms. The technological features disclosed herein works in the space of two-dimensional (2D) occupancy grids and plans in motor command space using a black box forward model for state inference. Compared to the conventional methods and systems, the inventive methods and systems disclosed herein include several properties that make it scalable and applicable to a production environment.

Abstract: Apparatus and methods for training and controlling of e.g., robotic devices. In one implementation, a robot may be utilized to perform a target task characterized by a target trajectory. The robot may be trained by a user using supervised learning. The user may interface to the robot, such as via a control apparatus configured to provide a teaching signal to the robot. The robot may comprise an adaptive controller comprising a neuron network, which may be configured to generate actuator control commands based on the user input and output of the learning process. During one or more learning trials, the controller may be trained to navigate a portion of the target trajectory. Individual trajectory portions may be trained during separate training trials. Some portions may be associated with robot executing complex actions and may require additional training trials and/or more dense training input compared to simpler trajectory actions.

Abstract: Robotic devices may be trained by a user guiding the robot along a target trajectory using a correction signal. A robotic device may comprise an adaptive controller configured to generate control commands based on one or more of the trainer input, sensory input, and/or performance measure. Training may comprise a plurality of trials. During an initial portion of a trial, the trainer may observe robot's operation and refrain from providing the training input to the robot. Upon observing a discrepancy between the target behavior and the actual behavior during the initial trial portion, the trainer may provide a teaching input (e.g., a correction signal) configured to affect robot's trajectory during subsequent trials. Upon completing a sufficient number of trials, the robot may be capable of navigating the trajectory in absence of the training input.

Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.

Abstract: Systems and methods for initializing a robot to autonomously travel a route are disclosed. In some exemplary implementations, a robot can detect an initialization object and then determine its position relative to that initialization object. The robot can then learn a route by user demonstration, where the robot associates actions along that route with positions relative to the initialization object. The robot can later detect the initialization object again and determine its position relative to that initialization object. The robot can then autonomously navigate the learned route, performing actions associated with positions relative to the initialization object.

Abstract: 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.

Abstract: Apparatus and methods for a modular robotic device with artificial intelligence that is receptive to training controls. In one implementation, modular robotic device architecture may be used to provide all or most high cost components in an autonomy module that is separate from the robotic body. The autonomy module may comprise controller, power, actuators that may be connected to controllable elements of the robotic body. The controller may position limbs of the toy in a target position. A user may utilize haptic training approach in order to enable the robotic toy to perform target action(s). Modular configuration of the disclosure enables users to replace one toy body (e.g., the bear) with another (e.g., a giraffe) while using hardware provided by the autonomy module. Modular architecture may enable users to purchase a single AM for use with multiple robotic bodies, thereby reducing the overall cost of ownership.

Abstract: Systems and methods for robotic mapping are disclosed. In some exemplary implementations, a robot can travel in an environment. From travelling in the environment, the robot can create a graph comprising a plurality of nodes, wherein each node corresponds to a scan taken by a sensor of the robot at a location in the environment. In some exemplary implementations, the robot can generate a map of the environment from the graph. In some cases, to facilitate map generation, the robot can constrain the graph to start and end at a substantially similar location. The robot can also perform scan matching on extended scan groups, determined from identifying overlap between scans, to further determine the location of features in a map.

Abstract: Systems and methods for training a robot to autonomously travel a route. In one embodiment, a robot can detect an initial placement in an initialization location. Beginning from the initialization location, the robot can create a map of a navigable route and surrounding environment during a user-controlled demonstration of the navigable route. After the demonstration, the robot can later detect a second placement in the initialization location, and then autonomously navigate the navigable route. The robot can then subsequently detect errors associated with the created map. Methods and systems associated with the robot are also disclosed.

Abstract: Systems and methods for initializing a robot to autonomously travel a route are disclosed. In some exemplary implementations, a robot can detect an initialization object and then determine its position relative to that initialization object. The robot can then learn a route by user demonstration, where the robot associates actions along that route with positions relative to the initialization object. The robot can later detect the initialization object again and determine its position relative to that initialization object. The robot can then autonomously navigate the learned route, performing actions associated with positions relative to the initialization object.

Abstract: Systems and methods for detection of people are disclosed. In some exemplary implementations, a robot can have a plurality of sensor units. Each sensor unit can be configured to generate sensor data indicative of a portion of a moving body at a plurality of times. Based on at least the sensor data, the robot can determine that the moving body is a person by at least detecting the motion of the moving body and determining that the moving body has characteristics of a person. The robot can then perform an action based at least in part on the determination that the moving body is a person.

Abstract: Apparatus and methods for a modular robotic device with artificial intelligence that is receptive to training controls. In one implementation, modular robotic device architecture may be used to provide all or most high cost components in an autonomy module that is separate from the robotic body. The autonomy module may comprise controller, power, actuators that may be connected to controllable elements of the robotic body. The controller may position limbs of the toy in a target position. A user may utilize haptic training approach in order to enable the robotic toy to perform target action(s). Modular configuration of the disclosure enables users to replace one toy body (e.g., the bear) with another (e.g., a giraffe) while using hardware provided by the autonomy module. Modular architecture may enable users to purchase a single AM for use with multiple robotic bodies, thereby reducing the overall cost of ownership.

Abstract: Systems and methods for dynamic route planning in autonomous navigation are disclosed. In some exemplary implementations, a robot can have one or more sensors configured to collect data about an environment including detected points on one or more objects in the environment. The robot can then plan a route in the environment, where the route can comprise one or more route poses. The route poses can include a footprint indicative at least in part of a pose, size, and shape of the robot along the route. Each route pose can have a plurality of points therein. Based on forces exerted on the points of each route pose by other route poses, objects in the environment, and others, each route poses can reposition. Based at least in part on interpolation performed on the route poses (some of which may be repositioned), the robot can dynamically route.

Abstract: Apparatus and methods for training and operating of robotic devices. Robotic controller may comprise a predictor apparatus configured to generate motor control output. The predictor may be operable in accordance with a learning process based on a teaching signal comprising the control output. An adaptive controller block may provide control output that may be combined with the predicted control output. The predictor learning process may be configured to learn the combined control signal. Predictor training may comprise a plurality of trials. During initial trial, the control output may be capable of causing a robot to perform a task. During intermediate trials, individual contributions from the controller block and the predictor may be inadequate for the task. Upon learning, the control knowledge may be transferred to the predictor so as to enable task execution in absence of subsequent inputs from the controller. Control output and/or predictor output may comprise multi-channel signals.

Abstract: An apparatus and methods for training and/or operating a robotic device to perform a composite task comprising a plurality of subtasks. Subtasks may be arranged in a hierarchy. Individual tasks of the hierarchy may be operated by a respective learning controller. Individual learning controllers may interface to appropriate components of feature extractor configured to detect features in sensory input. Individual learning controllers may be trained to produce activation output based on occurrence of one or more relevant features and using training input. Output of a higher level controller may be provided as activation indication to one or more lower level controllers. Inactive activation indication may be utilized to deactivate one or more components thereby improving operational efficiency. Output of a given feature extractor may be shared between two or more learning controllers.

Abstract: Robotic devices may be trained by a user guiding the robot along target action trajectory using an input signal. A robotic device may comprise an adaptive controller configured to generate control signal based on one or more of the user guidance, sensory input, performance measure, and/or other information. Training may comprise a plurality of trials, wherein for a given context the user and the robot's controller may collaborate to develop an association between the context and the target action. Upon developing the association, the adaptive controller may be capable of generating the control signal and/or an action indication prior and/or in lieu of user input. The predictive control functionality attained by the controller may enable autonomous operation of robotic devices obviating a need for continuing user guidance.

Abstract: 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.

Abstract: A robot may be trained by a user guiding the robot along target trajectory using a control signal. A robot may comprise an adaptive controller. The controller may be configured to generate control commands based on the user guidance, sensory input and a performance measure. A user may interface to the robot via an adaptively configured remote controller. The remote controller may comprise a mobile device, configured by the user in accordance with phenotype and/or operational configuration of the robot. The remote controller may detect changes in the robot phenotype and/or operational configuration. The remote controller may comprise multiple control elements configured to activate respective portions of the robot platform. Based on training, the remote controller may configure composite controls configured based two or more of control elements. Activation of a composite control may enable the robot to perform a task.