View source for 18240124. ROBOT NAVIGATION IN DEPENDENCE ON GESTURE(S) OF HUMAN(S) IN ENVIRONMENT WITH ROBOT simplified abstract (Google LLC)

=ROBOT NAVIGATION IN DEPENDENCE ON GESTURE(S) OF HUMAN(S) IN ENVIRONMENT WITH ROBOT=


==Organization Name==

[[:Category:Google LLC|Google LLC]]


[[Category:Google LLC]]

==Inventor(s)==

[[:Category:Catie Cuan of Stanford CA (US)|Catie Cuan of Stanford CA (US)]][[Category:Catie Cuan of Stanford CA (US)]]

[[:Category:Tsang-Wei Lee of Mountain View CA (US)|Tsang-Wei Lee of Mountain View CA (US)]][[Category:Tsang-Wei Lee of Mountain View CA (US)]]

[[:Category:Anthony G. Francis, Jr. of Simpsonville SC (US)|Anthony G. Francis, Jr. of Simpsonville SC (US)]][[Category:Anthony G. Francis, Jr. of Simpsonville SC (US)]]

[[:Category:Alexander Toshev of San Francisco CA (US)|Alexander Toshev of San Francisco CA (US)]][[Category:Alexander Toshev of San Francisco CA (US)]]

[[:Category:Soeren Pirk of Palo Alto CA (US)|Soeren Pirk of Palo Alto CA (US)]][[Category:Soeren Pirk of Palo Alto CA (US)]]

==ROBOT NAVIGATION IN DEPENDENCE ON GESTURE(S) OF HUMAN(S) IN ENVIRONMENT WITH ROBOT - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18240124 titled 'ROBOT NAVIGATION IN DEPENDENCE ON GESTURE(S) OF HUMAN(S) IN ENVIRONMENT WITH ROBOT

==Simplified Explanation==

Training and/or utilizing a high-level neural network (NN) model, such as a sequential NN model. The high-level NN model, when trained, can be used to process a sequence of consecutive state data instances (e.g., N most recent, including a current state date instance) to generate a sequence of outputs that indicate a sequence of position deltas. The sequence of position deltas can be used to generate an intermediate target position for navigation and, optionally, an intermediate target orientation that corresponds to the intermediate target position. The intermediate target position and, optionally, the intermediate target orientation, can be provided to a low-level navigation policy, such as an MPC policy, and used by the low-level navigation policy as its goal position (and optionally goal orientation) for a plurality of iterations (e.g., until a new intermediate target position (and optionally new target orientation) is generated using the high-level NN model.

* High-level neural network model trained to process consecutive state data instances
* Generates sequence of position deltas for navigation
* Intermediate target position and orientation provided to low-level navigation policy
* Used as goal position for navigation iterations

== Potential Applications ==
* Autonomous vehicles navigation
* Robotics path planning
* Drone flight control

== Problems Solved ==
* Efficient navigation goal setting
* Seamless integration of high-level and low-level navigation systems

== Benefits ==
* Improved navigation accuracy
* Real-time decision-making capabilities
* Enhanced autonomous operation

== Potential Commercial Applications of this Technology ==
Optimizing delivery routes for logistics companies

== Possible Prior Art ==
A similar approach was used in the field of robotics for path planning algorithms in the past.

== Unanswered Questions ==

=== How does the high-level NN model handle noisy or incomplete data instances during training? ===
The article does not address the specific methods or techniques used to handle noisy or incomplete data instances during training.

=== What is the computational cost associated with training and utilizing the high-level NN model for navigation tasks? ===
The article does not provide information on the computational resources required for training and using the high-level NN model in navigation applications.


==Original Abstract Submitted==

Training and/or utilizing a high-level neural network (NN) model, such as a sequential NN model. The high-level NN model, when trained, can be used to process a sequence of consecutive state data instances (e.g., N most recent, including a current state date instance) to generate a sequence of outputs that indicate a sequence of position deltas. The sequence of position deltas can be used to generate an intermediate target position for navigation and, optionally, an intermediate target orientation that corresponds to the intermediate target position. The intermediate target position and, optionally, the intermediate target orientation, can be provided to a low-level navigation policy, such as an MPC policy, and used by the low-level navigation policy as its goal position (and optionally goal orientation) for a plurality of iterations (e.g., until a new intermediate target position (and optionally new target orientation) is generated using the high-level NN model.



[[Category:G05D1/02]]
[[Category:G06V10/80]]
[[Category:G06V10/82]]
[[Category:G06V40/20]]