Abstract: An apparatus and methods for training and/or operating a robotic device to follow a trajectory. A robotic vehicle may utilize a camera and stores the sequence of images of a visual scene seen when following a trajectory during training in an ordered buffer. Motor commands associated with a given image may be stored. During autonomous operation, an acquired image may be compared with one or more images from the training buffer in order to determine the most likely match. An evaluation may be performed in order to determine if the image may correspond to a shifted (e.g., left/right) version of a stored image as previously observed. If the new image is shifted left, right turn command may be issued. If the new image is shifted right then left turn command may be issued.

Abstract: Robotic devices may be trained by a trainer guiding the robot along a target trajectory using physical contact with the robot. The robot 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. The trainer may observe task execution by the robot. Responsive to observing a discrepancy between the target behavior and the actual behavior, the trainer may provide a teaching input via a haptic action. The robot may execute the action based on a combination of the internal control signal produced by a learning process of the robot and the training input. The robot may infer the teaching input based on a comparison of a predicted state and actual state of the robot. The robot's learning process may be adjusted in accordance with the teaching input so as to reduce the discrepancy during a subsequent trial.

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: Apparatus and methods for training of robotic devices. Robotic devices may be trained by a user guiding the robot along target trajectory using an input signal. A robotic device may comprise an adaptive controller configured to generate control commands based on one or more of the user guidance, sensory input, and/or performance measure. Training may comprise a plurality of trials. During first trial, the user input may be sufficient to cause the robot to complete the trajectory. During subsequent trials, the user and the robot's controller may collaborate so that user input may be reduced while the robot control may be increased. Individual contributions from the user and the robot controller during training may be may be inadequate (when used exclusively) to complete the task.

Abstract: Apparatus and methods for developing robotic controllers comprising parallel networks. In some implementations, a parallel network may comprise at least first and second neuron layers. The second layer may be configured to determine a measure of discrepancy (error) between a target network output and actual network output. The network output may comprise control signal configured to cause a task execution by the robot. The error may be communicated back to the first neuron layer in order to adjust efficacy of input connections into the first layer. The error may be encoded into spike latency using linear or nonlinear encoding. Error communication and control signal provision may be time multiplexed so as to enable target action execution. Efficacy associated with forward and backward/reverse connections may be stored in individual arrays. A synchronization mechanism may be employed to match forward/reverse efficacy in order to implement plasticity.

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: 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: Event-based updates in artificial neuron networks may be implemented. An internal event may be defined in order to update incoming connections of a neuron. The internal event may be triggered by an external signal and/or internally by the neuron. A reinforcement signal may be used to trigger an internal event of a neuron in order to perform synaptic updates without necessitating post-synaptic response. An external event may be defined in order to deliver response of the neuron to desired targets. The external and internal events may be combined into a composite event configured to effectuate connection update and spike delivery to post-synaptic target. The scope of the internal event may comprise the respective neuron and does not extend to other neurons of the network. Conversely, the scope of the external event may extend to other neurons of the network via, for example, post-synaptic spike delivery.

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: Apparatus and methods for event based communication in a spiking neuron network. The network may comprise units communicating by spikes via synapses. The spikes may communicate a payload data. The data may comprise one or more bits. The payload may be stored in a buffer of a pre-synaptic unit and be configured to accessed by the post-synaptic unit. Spikes of different payload may cause different actions by the recipient unit. Sensory input spikes may cause postsynaptic response and trigger connection efficacy update. Teaching input spikes trigger the efficacy update without causing the post-synaptic response.

Abstract: Apparatus and methods for developing parallel networks. Parallel network design may comprise a general purpose language (GPC) code portion and a network description (ND) portion. GPL tools may be utilized in designing the network. The GPL tools may be configured to produce network specification language (NSL) engine adapted to generate hardware optimized machine executable code corresponding to the network description. The developer may be enabled to describe a parameter of the network. The GPC portion may be automatically updated consistent with the network parameter value. The GPC byte code may be introspected by the NSL engine to provide the underlying source code that may be automatically reinterpreted to produce the hardware optimized machine code. The optimized machine code may be executed in parallel.

Abstract: Apparatus and methods for developing parallel networks. In some implementations, a network may be partitioned into multiple partitions, wherein individual portions are being executed by respective threads executed in parallel. Individual portions may comprise multiple neurons and synapses. In order to reduce cross-thread traffic and/or reduce number of synchronization locks, network may be partitioned such that for given network portion, the neurons and the input synapses into neurons within the portion are executed within the same thread. Synapse update rules may be configured to allow memory access for postsynaptic neurons and forbid memory access to presynaptic neurons. Individual threads may be afforded pairs of memory buffers configured to effectuate asynchronous data input/output to/from thread. During an even iteration of network operation, even buffer may be utilized to store data generated by the thread during even iteration.

Abstract: Apparatus and methods for training of robotic devices. Robotic devices may be trained by a user guiding the robot along target trajectory using an input signal. A robotic device may comprise an adaptive controller configured to generate control commands based on one or more of the user guidance, sensory input, and/or performance measure. Training may comprise a plurality of trials. During first trial, the user input may be sufficient to cause the robot to complete the trajectory. During subsequent trials, the user and the robot's controller may collaborate so that user input may be reduced while the robot control may be increased. Individual contributions from the user and the robot controller during training may be may be inadequate (when used exclusively) to complete the task. Upon learning, user's knowledge may be transferred to the robot's controller to enable task execution in absence of subsequent inputs from the user.

Abstract: Adaptive controller apparatus of a plant may be implemented. The controller may comprise an encoder block and a control block. The encoder may utilize basis function kernel expansion technique to encode an arbitrary combination of inputs into spike output. The controller may comprise spiking neuron network operable according to reinforcement learning process. The network may receive the encoder output via a plurality of plastic connections. The process may be configured to adaptively modify connection weights in order to maximize process performance, associated with a target outcome. The relevant features of the input may be identified and used for enabling the controlled plant to achieve the target outcome.

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: Apparatus and methods for developing parallel networks. Parallel network design may comprise a general purpose language (GPC) code portion and a network description (ND) portion. GPL tools may be utilized in designing the network. The GPL tools may be configured to produce network specification language (NSL) engine adapted to generate hardware optimized machine executable code corresponding to the network description. The developer may be enabled to describe a parameter of the network. The GPC portion may be automatically updated consistent with the network parameter value. The GPC byte code may be introspected by the NSL engine to provide the underlying source code that may be automatically reinterpreted to produce the hardware optimized machine code. The optimized machine code may be executed in parallel.

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: Efficient updates of connections in artificial neuron networks may be implemented. A framework may be used to describe the connections using a linear synaptic dynamic process, characterized by stable equilibrium. The state of neurons and synapses within the network may be updated, based on inputs and outputs to/from neurons. In some implementations, the updates may be implemented at regular time intervals. In one or more implementations, the updates may be implemented on-demand, based on the network activity (e.g., neuron output and/or input) so as to further reduce computational load associated with the synaptic updates. The connection updates may be decomposed into multiple event-dependent connection change components that may be used to describe connection plasticity change due to neuron input. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.

Abstract: Generalized state-dependent learning framework in artificial neuron networks may be implemented. A framework may be used to describe plasticity updates of neuron connections based on connection state term and neuron state term. The state connections within the network may be updated based on inputs and outputs to/from neurons. The input connections of a neuron may be updated using connection traces comprising a time-history of inputs provided via the connections. Weights of the connections may be updated and connection state may be time varying. The updated weights may be determined using a rate of change of the trace and a term comprising a product of a per-neuron contribution and a per-connection contribution configured to account for the state time-dependency. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.

Abstract: Spiking neuron network conditionally independent subset classifier apparatus and methods. In some implementations, the network may comprise one or more subset neuron layers configured to determine presence of one or more features in the subset of plurality of conditionally independent features. The output of the subset layer may be coupled to an aggregation layer. State of the subset layer may be configured during training based on training input and a reference signal. During operation, spiking output of the subset layer may be combined by the aggregation layer to produce classifier output. Subset layer output and/or classifier output may be encoded using spike rate, latency, and/or base-n encoding.