Search

CN-121199998-B - 5G cross-domain low-delay remote control system and method for explosion-proof humanoid robot

CN121199998BCN 121199998 BCN121199998 BCN 121199998BCN-121199998-B

Abstract

The invention belongs to the technical field of remote control of robots, and particularly relates to a 5G cross-domain low-time-delay remote control system and method for an explosion-proof humanoid robot. The system comprises a main teleoperation intelligent cabin and a slave remote explosion-proof humanoid robot, wherein the main teleoperation intelligent cabin and the slave remote explosion-proof humanoid robot are in information interaction through a 5G network, video streams are transmitted through H.264 codes and WebRTC protocols, sensor data are packed through JSON, and humanoid control and chassis control information are independently processed. The invention can realize accurate remote force feedback and control, the humanoid control time delay is within 100ms, the chassis control time delay is within 150ms, the stability and time delay problems of remote cross-domain control are effectively solved, and the personal safety of operators in dangerous operation environments is ensured.

Inventors

  • MIN JIHAI
  • LIU SHUANG
  • WANG JIE
  • YANG JIASHUAI
  • FEI KE

Assignees

  • 南京天创智能科技股份有限公司

Dates

Publication Date
20260508
Application Date
20251009

Claims (7)

  1. 1. An explosion-proof humanoid robot 5G cross-domain low-delay remote control system, characterized by comprising: the main end teleoperation intelligent cabin is used for an operator to remotely send a control instruction and receive feedback information; the slave-end remote explosion-proof humanoid robot comprises a mobile chassis and a humanoid robot and is used for executing a control instruction sent by the main-end teleoperation intelligent cabin and feeding back information; The communication system based on the 5G network is used for establishing a 5G communication channel between the main-end teleoperation intelligent cabin and the slave-end remote explosion-proof humanoid robot so as to transmit control instructions and feedback information; Wherein, the humanoid robot and the mobile chassis adopt a separated architecture on hardware, and respective control instructions and feedback information are transmitted by adopting independent 5G communication channels; the communication system adopts protocol optimization and a machine learning-based anti-weak network algorithm, wherein the protocol optimization comprises the steps of adopting a user-defined lightweight protocol based on UDP to replace TCP, realizing a retransmission mechanism based on serial numbers and selective confirmation for key data in an application layer, adopting an ROHC algorithm to compress an IP/UDP packet header, and embedding a CRC32 check code into an application layer data packet to perform end-to-end check; The remote operation intelligent cabin of the slave end comprises a seat for an operator to sit and stand, a remote operation device for controlling the upper limb action of the slave end remote explosion-proof humanoid robot, a driving control device for controlling the movement and the steering of the mobile chassis, a display for displaying the environment information and the robot state transmitted by the slave end remote explosion-proof humanoid robot in real time, a master end intelligent terminal for data processing, a master end 5G router for carrying out 5G communication with the slave end intelligent terminal, and a slave end remote operation intelligent terminal for carrying out remote operation on the remote explosion-proof humanoid robot; The remote anti-explosion humanoid robot at the slave end comprises a four-wheel drive wheel type mobile chassis with omnidirectional movement capability, a humanoid robot, a sensor assembly, a plurality of cameras, a slave-end intelligent terminal, a 5G communication module and a 5G communication module, wherein the humanoid robot is provided with a humanoid main body, a humanoid double arm and a tail end clamping jaw arranged at the tail end of the double arm; The main intelligent terminal responds to the operation of the driving control device, converts a control instruction into linear speed and angular speed information, and transmits the linear speed and angular speed information to the mobile chassis intelligent terminal through a 5G communication channel to control the movement and steering of the mobile chassis; The intelligent terminal of the humanoid robot acquires force and moment information acquired by a six-dimensional force sensor arranged at the tail end clamping jaw in real time, and after low-pass filtering treatment, the transmission delay and the dynamic interference are counteracted by combining a state observer and feedforward dynamic compensation through a bilateral control algorithm, a force feedback result is transmitted to the intelligent terminal of the main end through a 5G communication channel, and a force feedback feeling is provided for an operator through the remote control device so as to realize master-slave force feedback closed-loop operation; The bilateral control algorithm comprises taking the pose of a main end as the expected pose of a slave end through a forward channel, taking the measured force of the slave end as the feedback force of the main end through a reverse channel, and adopting a reverse kinematics algorithm to carry out model reverse solution; The impedance model adopted by the inverse kinematics algorithm is as follows: , Wherein, the In order for the force to be desired, 、 、 Respectively a desired inertia matrix, damping matrix and stiffness matrix, 、 、 Respectively position error, speed error and acceleration error by regulating damping matrix in impedance model And stiffness matrix The slave-end humanoid robot presents different compliance characteristics so as to process dynamic model differences between the master end and the slave end; The state observer adopts Long Beige observer, and the mathematical model is as follows: , Wherein the method comprises the steps of Is the state vector of the estimate and, Is the derivative of the estimated state, A, B, C is the system matrix, the input matrix, the output matrix, Is a delay of Is provided with a control input for the control of the (c), Is a delay of L is the observer gain matrix; The compensation term calculation formula of the feedforward dynamic compensation is as follows , wherein, Is the feed-forward compensation torque and, Is the joint position vector, which is the position vector, Is the velocity vector of the joint and, 、 Is the desired joint acceleration and velocity, Is an inertial matrix of the mass of the material, Is a matrix of coriolis and centrifugal forces, Is the gravity vector, the compensation term obtained by calculation For compensating inertial forces involving the humanoid robot itself Gravity force Coriolis and centrifugal forces Kinetic effects, among others.
  2. 2. The explosion-proof humanoid robot 5G cross-domain low-delay remote control system according to claim 1, wherein in the separated control architecture, a humanoid robot intelligent terminal adopts an inflight Jetson Nano processor to control the humanoid robot, a mobile chassis intelligent terminal adopts a raspberry pie processor to control the mobile chassis, and the mobile chassis intelligent terminal is communicated with a master intelligent terminal through a slave 5G router and a 5G module respectively.
  3. 3. The explosion-proof humanoid robot 5G cross-domain low-delay remote control system according to claim 2, wherein the communication system is used for realizing cross-domain information interaction between a master-end teleoperation intelligent cabin and a slave-end remote explosion-proof humanoid robot, including video streaming transmission, sensor data feedback, control instruction transmission and force feedback; Different data types set different quality of service markers, wherein robot joint motor position torque data and sensor data are transmitted over UDP and prior to video streaming over TCP.
  4. 4. The explosion-proof humanoid robot 5G cross-domain low-delay remote control system according to claim 3, wherein the humanoid robot intelligent terminal transmits a plurality of camera video streams through h.264 coding and WebRTC protocol, and sensor data including an odometer, an IMU inertial measurement unit and a laser radar are transmitted in real time through JSON packaging.
  5. 5. The anti-explosion humanoid robot 5G cross-domain low-delay remote control system according to claim 1 is characterized in that the UDP-based custom lightweight protocol eliminates delay caused by TCP handshake, retransmission and congestion control, a retransmission mechanism based on sequence numbers and selective acknowledgement is realized at an application layer, wherein when a receiving party detects that a data packet is lost, only the lost data packet is requested to be retransmitted, a CRC32 check code is embedded at the application layer for end-to-end check, and the selective retransmission is triggered if the check of a key data packet by the receiving party fails.
  6. 6. The explosion-proof humanoid robot 5G cross-domain low-latency remote control system according to claim 5, wherein the weak network algorithm combines on-line supervised learning and deep reinforcement learning, models resource scheduling as a markov decision process, uses real-time and predicted network states as state inputs, uses communication parameter adjustment as action outputs, and uses minimum latency and maintenance reliability as rewarding targets, wherein the state inputs include latency, packet loss rate, bandwidth and signal strength, and the action outputs include modulation scheme adjustment, power control and frequency band switching.
  7. 7. The method of an explosion-proof humanoid robot 5G cross-domain low-latency remote control system of claim 1, comprising the steps of: S1, establishing a master-slave communication connection and control architecture: a teleoperation intelligent cabin is built at a master end, a master end intelligent terminal is arranged, a remote explosion-proof humanoid robot is built at a slave end, and a humanoid robot intelligent terminal and a mobile chassis intelligent terminal are arranged; Establishing a communication connection based on a 5G network, and adopting a separated control architecture to separate the humanoid robot control from the mobile chassis control, wherein a main-end intelligent terminal and the humanoid robot intelligent terminal communicate through a 5G router, and the main-end intelligent terminal and the mobile chassis intelligent terminal communicate through a 5G module; s2, executing chassis movement control: the main intelligent terminal converts the operation data of the driving control device into linear speed and angular speed information in real time, the linear speed and the angular speed information are transmitted to the mobile chassis intelligent terminal through a 5G communication channel, and the mobile chassis intelligent terminal controls the movement and the steering of the mobile chassis; s3, performing teleoperation control of the humanoid robot: The master intelligent terminal acquires the joint motor position, torque and clamping jaw control information of the remote teleoperation device in real time, and transmits the information to the slave humanoid robot through a 5G communication channel, so that synchronous motion control of the double arms and the clamping jaws is realized; s4, video and sensor data transmission is carried out: The intelligent terminal of the humanoid robot collects video streams through a plurality of cameras and transmits the video streams to the intelligent terminal of the main end in real time for decoding and displaying; s5, implementing force feedback processing: The intelligent terminal of the humanoid robot acquires the position, moment and six-dimensional force sensor information of a humanoid joint motor in real time, a low-pass filter is applied to eliminate high-frequency noise, a force feedback result is calculated through a bilateral control algorithm and is transmitted to the intelligent terminal of the main end through a 5G communication channel, and a force feedback feeling is provided for an operator by the remote control device so as to realize master-slave force feedback closed-loop operation; s6, executing protocol and resource scheduling optimization: optimizing a transmission protocol at a protocol layer, wherein the transmission protocol comprises the steps of adopting a user-defined lightweight protocol based on UDP to replace TCP, realizing a retransmission mechanism based on serial numbers and selective confirmation for key data at an application layer, adopting an ROHC algorithm to compress an IP/UDP packet header, and embedding a CRC32 check code into an application layer data packet to perform end-to-end check so as to reduce transmission overhead and time delay; And introducing a machine learning-based anti-weak network algorithm into a resource scheduling and management layer, and dynamically adjusting a modulation mode, power and frequency band by predicting network congestion and channel state so as to balance time delay and energy efficiency.

Description

5G cross-domain low-delay remote control system and method for explosion-proof humanoid robot Technical Field The invention belongs to the robot remote control technology, and particularly relates to an explosion-proof humanoid robot 5G cross-domain low-time-delay remote control system and method. Background The 5G technology, particularly its ultra-reliable low latency communication (URLLC) feature, is opening up a new path for cross-domain low latency remote control. At present, the technology has been developed in core scenes such as industrial automation (such as port gantry crane and mining truck remote control), remote operation, accurate load control of a power grid, intelligent traffic road coordination and the like. The core of the method is that the control terminals (such as operation cabins) deployed in different regions (possibly crossing cities, provinces and even national boundaries) are efficiently connected with the execution terminals (such as mechanical arms, unmanned aerial vehicles and vehicles) by utilizing millisecond-level (theoretically up to 1 ms) end-to-end time delay, ultra-high reliability and wide area coverage capability of the 5G network, so that real-time and accurate man-machine interaction or automatic control of remote equipment is realized. This represents a significant evolution of teleoperational technology from traditional dedicated wired networks or more limited local wireless networks to wide area flexible deployment based on public mobile communications. The current level of robot intelligence is still limited and it is difficult to rival human intelligence. Therefore, in the field of dangerous operations (such as explosion venting, aerospace and nuclear power), the exploration of how to integrate human intelligence into a robot for remote control has great significance. The man-machine cooperation mode can effectively ensure personnel safety, fully exert real-time decision making capability of human beings and has remarkable application value. The traditional wired teleoperation connection mode is stable, but the network cable constrains the flexibility of the equipment, and the deployment is relatively complicated. The 5G technology is adopted to replace wired connection, so that the operation flexibility and the deployment convenience can be remarkably improved. The prior art has the following problems that the traditional wired teleoperation mode is poor in flexibility and complex in deployment, the requirement of cross-domain remote control cannot be met, the time delay of the traditional wireless teleoperation system is high, real-time accurate control is difficult to achieve, the problems of time delay jitter and packet loss caused by unstable network in the cross-domain remote control are serious, an effective force feedback mechanism is lacking, an operator cannot obtain real tactile feedback, the stability and the reliability of the system are to be improved, and the system is difficult to adapt to a severe communication environment. Disclosure of Invention The invention aims to provide a 5G cross-domain low-time-delay remote control system and method for an explosion-proof humanoid robot, aiming at the defects of the prior art, so as to solve the problems of high time delay, poor stability, lack of effective force feedback and the like in the prior art and realize safe and reliable remote control in dangerous operation environments. The technical scheme is that in order to achieve the purpose, the 5G cross-domain low-time-delay remote control system of the explosion-proof humanoid robot comprises: the main end teleoperation intelligent cabin is used for an operator to remotely send a control instruction and receive feedback information; The slave-end remote explosion-proof humanoid robot comprises a mobile chassis and a humanoid main body and is used for executing a control instruction sent by the main-end teleoperation intelligent cabin; the communication system based on the 5G network is used for realizing 5G communication between the remote operation intelligent cabin of the master end and the remote explosion-proof humanoid robot of the slave end; Wherein, the humanoid main body and the mobile chassis adopt a separated architecture on hardware, and respective control instruction information is transmitted by adopting an independent 5G communication channel; the communication system adopts protocol optimization and a machine learning-based anti-weak network algorithm, the protocol optimization comprises the steps of adopting a user-defined lightweight protocol based on UDP to replace TCP, realizing a retransmission mechanism based on serial numbers and selective confirmation for key data in an application layer, adopting an ROHC algorithm to compress an IP/UDP packet header, embedding a CRC32 check code into an application layer data packet to perform end-to-end check, and the anti-weak network algorithm predicts network congestion and channel state t