Tele-Robot Voice Control With Operator-Only Command Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In collaborative multi-presence telepresence systems, tele-robots struggle to differentiate between operators and observers, leading to incorrect command execution and excessive energy consumption due to continuous speech recognition from multiple users.
Innovation Solution
A robotic telepresence system with an ASR cloud and dedicated bidirectional WebSocket P2P connections differentiates between operator and observer speech signals, enabling efficient command recognition and transmission only to the tele-robot, reducing energy consumption and improving command alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the robot performs continuous speech recognition from all users in a multi-user telepresence session, then the robot can potentially receive commands from any user, but the robot cannot differentiate between operator commands and observer speech, leading to incorrect command execution and excessive energy consumption
Solution Approach 1:
The system segments speech processing by identifying and separating the operator's speech from other users' speech. The robot selectively processes only the operator's commands while filtering out observer speech, thereby reducing unnecessary speech recognition operations and conserving energy.
Solution Approach 2:
The system introduces an intermediary mechanism (speaker identification module) that mediates between multiple speech sources and the command processing system. This intermediary identifies which user is the operator and routes only their speech to the command execution system, preventing energy waste on processing irrelevant speech.
2Ease of operation
If the robot processes speech from all users simultaneously, then all users can communicate freely, but the robot executes commands from wrong persons due to inability to differentiate operator from observers
Solution Approach 1:
The system segments speech sources and assigns different processing paths: operator speech is routed to command execution while observer speech is filtered out. This segmentation maintains communication freedom for all users while ensuring only operator commands are executed, thereby improving reliability.
Solution Approach 2:
The system implements feedback mechanisms where the robot identifies the current operator and adjusts its speech processing behavior accordingly. This feedback loop ensures that command execution accuracy is maintained while allowing free communication among all participants.
3Speed
If the robot performs automatic speech recognition continuously, then commands can be recognized in real-time, but the resource-constrained robot drains energy quickly
Solution Approach 1:
Instead of continuous speech processing, the system employs periodic action by activating speech recognition only when the operator speaks. The robot monitors speech activity and triggers ASR selectively, maintaining real-time command recognition capability while significantly reducing energy consumption during non-command periods.
Solution Approach 2:
The system extracts and processes only the essential speech signals (operator commands) while discarding unnecessary speech from observers. This extraction approach maintains real-time responsiveness to commands while eliminating energy waste on processing irrelevant audio data.
Data Source
AI summary
Complexity of voice based control of tele-robots increases when used in collaborative multi-presence systems, as tele-robot fail to differentiate between operator and observers, and hence may end up executing command from wrong person. Further, the tele-robot ends up losing energy as it listens continuously to speech from multiple people, which may or may not contain commands. Embodiments disclosed herein provide a telepresence system in which an Automatic Speech Recognition (ASR) component hosted on a cloud receives and processes speech signals, infers commands, and only the inferred commands are transmitted to the tele-robot, thereby causing energy saving at the tele-robot end as it doesn't have to listen to all the speech from all the operator and observers for the execution of the voice based navigation control command. Further, a dedicated channel is established between the operator at any instance and the tele-robot, enabling direct communication between the operator and the tele-robot.