Adaptive, imitative navigational assistance
Abstract
Systems, methods, and computer program products for adaptive, imitation learning and applications to navigational assistance are disclosed. The inventive concepts include: generating a navigational assistance trajectory through a physical environment in response to receiving a request for navigational assistance through the physical environment; and transmitting navigation instructions to a mobile device. The navigation instructions are based at least in part on the navigational assistance trajectory. A user receiving the navigational assistance trajectory and auditory instructions may advantageously navigate through the complex, dynamic physical environment without relying on visual cues.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A computer-implemented method for adaptive imitation learning and navigational assistance, comprising:
generating a navigational assistance trajectory through a physical environment in response to receiving a request for navigational assistance through the physical environment; and transmitting navigation instructions to a mobile device for output of the navigation instructions to a user of the mobile device, wherein the navigation instructions are based at least in part on the navigational assistance trajectory.
2 . The computer-implemented method of claim 1 , wherein the navigation instructions comprise auditory instructions.
3 . The computer-implemented method of claim 1 , wherein the navigational assistance trajectory is based on some or all of a plurality of trajectories, each of the plurality of trajectories independently describing a path through at least a portion of the physical environment.
4 . The computer-implemented method of claim 3 , wherein the plurality of trajectories are received over a period of time, and wherein the navigational assistance trajectory reflects a most recent physical state of the physical environment.
5 . The computer-implemented method of claim 3 , wherein the plurality of trajectories are generated by a monitoring system observing one or more experts navigating through the physical environment.
6 . The computer-implemented method of claim 1 , wherein the navigational assistance trajectory is generated using a deep neural network-based imitation learning algorithm.
7 . The computer-implemented method of claim 1 , wherein the navigational assistance trajectory comprises a sequence of state/action pairs;
wherein each state corresponds to a location in the physical environment; and wherein each action corresponds to a movement from a current state to a next state in the sequence of state/action pairs.
8 . The computer-implemented method of claim 7 , wherein the states are represented by an n-dimensional observation space;
wherein the actions are represented by an m-dimensional action space; wherein at least some of the observation space dimensions are continuous and at least some other of the observation space dimensions are discrete; and wherein at least some of the action space dimensions are continuous and at least some other of the action space dimensions are discrete.
9 . The computer-implemented method of claim 1 , further comprising:
determining whether the mobile device is compliant with the navigational assistance trajectory; in response to determining the mobile device is non-compliant with the navigational assistance trajectory, generating a new navigational assistance trajectory through the physical environment; and wherein the new navigational assistance trajectory is based at least in part on:
at least one of a plurality of trajectories, each trajectory independently describing a path through at least a portion of the physical environment; and
a position of the mobile device at a time of determining the mobile device is non-compliant with the navigational assistance trajectory.
10 . A computer program product for adaptive, imitative navigational assistance, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor, to cause the processor to perform a method comprising:
generating, using the processor, a navigational assistance trajectory through a physical environment in response to receiving a request for navigational assistance through the physical environment; and transmitting navigation instructions to a mobile device for output of the navigation instructions to a user of the mobile device, wherein the navigation instructions are based at least in part on the navigational assistance trajectory.
11 . The computer program product of claim 10 , wherein the navigation instructions comprise auditory instructions.
12 . The computer program product of claim 10 , wherein the navigational assistance trajectory is based on some or all of a plurality of trajectories, each of the plurality of trajectories independently describing a path through at least a portion of the physical environment.
13 . The computer program product of claim 12 , wherein the plurality of trajectories are received over a period of time, and wherein the navigational assistance trajectory reflects a most recent physical state of the physical environment.
14 . The computer program product of claim 12 , wherein the plurality of trajectories are generated by the processor using a monitoring system observing one or more experts navigating through the physical environment.
15 . The computer program product of claim 10 , wherein the navigational assistance trajectory is generated by the processor using a deep neural network-based imitation learning algorithm.
16 . The computer program product of claim 10 , wherein the navigational assistance trajectory comprises a sequence of state/action pairs;
wherein each state corresponds to a location in the physical environment; and wherein each action corresponds to a movement from a current state to a next state in the sequence of state/action pairs.
17 . The computer program product of claim 16 , wherein the states are represented by an n-dimensional observation space;
wherein the actions are represented by an m-dimensional action space; wherein at least some of the observation space dimensions are continuous and at least some other of the observation space dimensions are discrete; and wherein at least some of the action space dimensions are continuous and at least some other of the action space dimensions are discrete.
18 . The computer program product of claim 10 , the method further comprising:
determining, using the processor, whether the mobile device is compliant with the navigational assistance trajectory; in response to determining the mobile device is non-compliant with the navigational assistance trajectory, generating, using the processor, a new navigational assistance trajectory through the physical environment; and wherein the new navigational assistance trajectory is based at least in part on:
at least one of a plurality of trajectories, each trajectory independently describing a path through at least a portion of the physical environment; and
a position of the mobile device at a time of determining the mobile device is non-compliant with the navigational assistance trajectory.
19 . A system for adaptive, imitative navigational assistance, comprising:
a processor; and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to: generate a navigational assistance trajectory through a physical environment in response to receiving a request for navigational assistance through the physical environment; and transmit navigation instructions to a mobile device for output of the navigation instructions to a user of the mobile device, wherein the navigation instructions are based at least in part on the navigational assistance trajectory.
20 . The system of claim 19 , wherein all data transmitted to the mobile device excludes any form of optical data, image data, and video data.Join the waitlist — get patent alerts
Track US2021190529A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.