CN-118105251-B - Intelligent wheelchair control method based on multi-sensor information fusion

CN118105251BCN 118105251 BCN118105251 BCN 118105251BCN-118105251-B

Abstract

The invention discloses an intelligent wheelchair control method based on multi-sensor information fusion, which comprises the steps of firstly collecting Hall rocker voltage signals, the distance between a wheelchair and an obstacle, obstacle images and wheelchair inertia data, then processing the data to obtain the position offset of the Hall rocker, the included angle between the advancing direction of the wheelchair and the center of the obstacle and the road surface inclination angle, fusing the distance between the wheelchair and the obstacle, the included angle between the advancing direction of the wheelchair and the center of the obstacle and the road surface inclination angle based on fuzzy control to obtain comprehensive environment coefficients, finally judging the running state of the wheelchair according to the position offset of the wheelchair, and carrying out information coupling on the gear information, the position offset and the comprehensive environment coefficients of the wheelchair, and calculating expected speeds of left and right wheels of the wheelchair under different running states. The method fully extracts the environment information, realizes the full coupling of the environment information, the wheelchair running state and the control signals, ensures the safety and the reliability of the wheelchair in running, and realizes the intelligent control of the wheelchair.

Inventors

QI KAICHENG
LI CHAO
YIN ZHIYANG
FU KEFEI
ZHANG JIANJUN
LIU TENG
GUO SHIJIE

Assignees

河北工业大学

Dates

Publication Date: 20260508
Application Date: 20240312

Claims (4)

1. An intelligent wheelchair control method based on multi-sensor information fusion is characterized by comprising the following steps: The first step, collecting data, including Hall rocker voltage signals, the distance between a wheelchair and an obstacle, an obstacle image and wheelchair inertia data; Processing the data to obtain the position offset of the Hall rocker, the included angle between the advancing direction of the wheelchair and the center of the obstacle and the inclination angle of the road surface; thirdly, fusing the distance between the wheelchair and the obstacle, the included angle between the advancing direction of the wheelchair and the center of the obstacle and the road surface inclination angle based on fuzzy control to obtain a comprehensive environmental coefficient; step four, calculating expected speeds of left and right wheels of the wheelchair in different running states; (1) When the absolute delta X and the absolute delta Y are smaller than or equal to the error threshold epsilon, the wheelchair is considered to be motionless when the Hall rocker is touched manually; (2) When the absolute value of delta Y is larger than the absolute value of c delta X, the wheelchair is in a straight running state, if delta Y is larger than epsilon, the wheelchair is in a straight running state, the expected speeds of the left wheel and the right wheel of the wheelchair are V l ＝V r = w.delta Y.K.m, and if delta Y is smaller than epsilon, the wheelchair is in a straight running state, and if delta Y is larger than epsilon, the expected speeds of the left wheel and the right wheel of the wheelchair are V l ＝V r = w.delta Y.K.m; (3) When the I delta Y I is less than 1/c I delta X I, the wheelchair is turned in situ, if delta X > epsilon, the wheelchair is turned in situ and the expected speeds of the left wheel and the right wheel are V l ＝w·ΔX·K·m,V r = w-delta X K.m respectively, and if delta X < -epsilon, the wheelchair is turned in situ and the expected speeds of the left wheel and the right wheel are V l ＝w·ΔX·K·m,V r = w-delta X K.m respectively; (4) When (-1/c) DeltaX < DeltaY < -cDeltaX or 1/c DeltaX < DeltaY < cDeltaX, and both DeltaX and DeltaY are larger than the error threshold epsilon, the wheelchair running state is turning in the forward direction, and the expected speeds of the left wheel and the right wheel are V l ＝w·(ΔY+b·ΔX)·K·m,V l = w (DeltaY-b-DeltaX) K-m respectively; (5) When cDeltaX < DeltaY < 1/cDeltaX or-cDeltaX < DeltaY < (-1/c) DeltaX, and both |DeltaX| and |DeltaY| are larger than the error threshold epsilon, the wheelchair running state is turning in the backward direction, and the expected speeds of the left wheel and the right wheel are V l ＝w·(ΔY+b·ΔX)·K·m,V l = w (DeltaY-b-DeltaX) K-m respectively; wherein (DeltaX, deltaY) is the position offset of the Hall rocker, c is a constant, V l is the expected speed of the left wheel of the wheelchair, V r is the expected speed of the right wheel of the wheelchair, K is the wheelchair gear coefficient, w is the proportionality coefficient, m is the comprehensive environment coefficient, b is a constant, deltaY+b.DeltaX is the left wheel command value, deltaY-b.DeltaX is the right wheel command value in the forward and backward turning, the command value is the regular motor positive rotation, and the command value is the negative motor reverse rotation.
2. The intelligent wheelchair control method based on multi-sensor information fusion according to claim 1, wherein the angle θ between the wheelchair forward direction and the center of the obstacle is calculated by the following formula: Wherein a 'is the width of the obstacle image, b' is the distance from the position of the center point of the obstacle in the image to the straight line of the wheelchair advancing direction, A range of angles is imaged for the camera.
3. The intelligent wheelchair control method based on multi-sensor information fusion according to claim 1 or 2, wherein the calculation formula of the road surface inclination angle γ is as follows: in the formula, And The components of the fused wheelchair poses at the moment k on the x, y and z axes respectively, Is the real part of the fused wheelchair pose.
4. The intelligent wheelchair control method based on multi-sensor information fusion according to claim 3, wherein the wheelchair inertia data comprises acceleration of an accelerometer and angular velocity of a gyroscope, the wheelchair gestures are calculated based on the acceleration and the angular velocity respectively, and the calculated gestures are fused to obtain a fused wheelchair gesture of the following formula; q est (k)＝σq r (k)+(1-σ)q ω (k) (17) Where q est (k) is the fusion wheelchair posture at time k, q r (k) is the wheelchair posture at time k obtained by the acceleration calculation, q ω (k) is the wheelchair posture at time k obtained by the angular velocity calculation, and σ e (0, 1) is the weight factor.

Description

Intelligent wheelchair control method based on multi-sensor information fusion Technical Field The invention belongs to the technical field of intelligent wheelchair control, and particularly relates to an intelligent wheelchair control method based on multi-sensor information fusion. Background The wheelchair is used as a common auxiliary tool for the elderly and patients with limb dysfunction to walk and travel, not only improves the life quality of the elderly and patients, but also reduces the burden of accompanying personnel. The existing electric wheelchair is mainly operated by people, realizes man-machine interaction in modes of operating levers, keys and the like, and needs to be operated by a user in combination with surrounding environment random strain in the use process, so that the intelligent degree is low. The intelligent wheelchair can detect environmental information through the sensor, and the controller sends out control signals based on analysis and processing of the environmental information to control the intelligent wheelchair, so that danger can be effectively avoided, and the intelligent wheelchair can run more reliably and safely. However, the existing intelligent wheelchair has single sensor, cannot fully reflect environmental information, and has low coupling degree between the running state of the wheelchair and the environmental information. Disclosure of Invention Aiming at the defects of the prior art, the invention aims to provide an intelligent wheelchair control method based on multi-sensor information fusion. The invention solves the technical problems by adopting the following technical scheme: An intelligent wheelchair control method based on multi-sensor information fusion is characterized by comprising the following steps: The first step, collecting data, including Hall rocker voltage signals, the distance between a wheelchair and an obstacle, an obstacle image and wheelchair inertia data; Processing the data to obtain the position offset of the Hall rocker, the included angle between the advancing direction of the wheelchair and the center of the obstacle and the inclination angle of the road surface; thirdly, fusing the distance between the wheelchair and the obstacle, the included angle between the advancing direction of the wheelchair and the center of the obstacle and the road surface inclination angle based on fuzzy control to obtain a comprehensive environmental coefficient; step four, calculating expected speeds of left and right wheels of the wheelchair in different running states; (1) When the absolute delta X and the absolute delta Y are smaller than or equal to the error threshold epsilon, the wheelchair is considered to be motionless when the Hall rocker is touched manually; (2) When the absolute value of delta Y is larger than the absolute value of c delta X, the wheelchair is in a straight running state, if delta Y is larger than epsilon, the wheelchair is in a straight running state, the expected speeds of the left wheel and the right wheel of the wheelchair are V l＝Vr = w.delta Y.K.m, and if delta Y is smaller than epsilon, the wheelchair is in a straight running state, and if delta Y is larger than epsilon, the expected speeds of the left wheel and the right wheel of the wheelchair are V l＝Vr = w.delta Y.K.m; (3) When the I delta Y I is less than 1/c I delta X I, the wheelchair is turned in situ, if delta X > epsilon, the wheelchair is turned in situ and the expected speeds of the left wheel and the right wheel are V l＝w·ΔX·K·m,Vr = w-delta X K.m respectively, and if delta X < -epsilon, the wheelchair is turned in situ and the expected speeds of the left wheel and the right wheel are V l＝w·ΔX·K·m,Vr = w-delta X K.m respectively; (4) When (-1/c) DeltaX < DeltaY < -cDeltaX or 1/c DeltaX < DeltaY < cDeltaX, and both DeltaX and DeltaY are larger than the error threshold epsilon, the wheelchair running state is turning in the forward direction, and the expected speeds of the left wheel and the right wheel are V l＝w·(ΔY+b·ΔX)·K·m,Vl = w (DeltaY-b-DeltaX) K-m respectively; (5) When cDeltaX < DeltaY < 1/cDeltaX or-cDeltaX < DeltaY < (-1/c) DeltaX, and both |DeltaX| and |DeltaY| are larger than the error threshold epsilon, the wheelchair running state is turning in the backward direction, and the expected speeds of the left wheel and the right wheel are V l＝w·(ΔY+b·ΔX)·K·m,Vl = w (DeltaY-b-DeltaX) K-m respectively; Wherein (DeltaX, deltaY) is the position offset of the Hall rocker, c is a constant, V l is the expected speed of the left wheel of the wheelchair, V r is the expected speed of the right wheel of the wheelchair, K is the gear coefficient of the wheelchair, w is the proportional coefficient, m is the non-comprehensive environmental coefficient, b is a constant, deltaY+b.DeltaX is the command value of the left wheel, deltaY-b.DeltaX is the command value of the right wheel in the forward and backward turning, the command value is positive rotation of