An ecologically-controlled exoskeleton can improve balance recovery after slippage

Abstract

The evolution to bipedalism forced humans to develop suitable strategies for dynamically controlling their balance, ensuring stability, and preventing falling. The natural aging process and traumatic events such as lower-limb loss can alter the human ability to control stability significantly increasing the risk of fall and reducing the overall autonomy. Accordingly, there is an urgent need, from both end-users and society, for novel solutions that can counteract the lack of balance, thus preventing falls among older and fragile citizens. In this study, we show a novel ecological approach relying on a wearable robotic device (the Active Pelvis Orthosis, APO) aimed at facilitating balance recovery after unexpected slippages. Specifically, if the APO detects signs of balance loss, then it supplies counteracting torques at the hips to assist balance recovery. Experimental tests conducted on eight elderly persons and two transfemoral amputees revealed that stability against falls improved due to the "assisting when needed" behavior of the APO. Interestingly, our approach required a very limited personalization for each subject, and this makes it promising for real-life applications. Our findings demonstrate the potential of closed-loop controlled wearable robots to assist elderly and disabled subjects and to improve their quality of life.

Figure 1. Control strategy.

(A) The mechatronic platform (1) provides sudden and unexpected slipping-like perturbations while the subject was steadily walking (2). The subject’s balance control was hence challenged (3) and, accordingly, the Active Pelvis Orthosis (4) could supply the assistive strategy for stability recovery. (B) The balance loss is detected in real time by an algorithm running in the APO control unit and comparing the actual hip angles of the robot (i.e., θ) with those predicted by a pool of adaptive oscillators (i.e., ). (C) Once the slipping-like perturbation was detected, counteracting torques were supplied by the APO at the hip joints to promote balance recovery. Panel C was created by Arch. Alessio Tommasetti Panel C was created by Mr. Francesco Giovacchini.

Figure 2. Real time detection of slipping-like perturbations.

(A) The adaptive-threshold based algorithm analyses the difference between measured (light green) and estimated (purple) hip joint angles. If the error signal (orange) is over the thresholds (dashed lines), a balance loss is detected. (B) Detection time obtained during the experimental trials for the elderly subjects and amputees (mean values ± SD).

Figure 3. Kinematic patterns at leg joints.

(A and B) Joint angles (hip, knee and ankle) at PL and UL are depicted for three experimental conditions, for one elderly subject and one amputee: i) steady locomotion (mean values ± SD, grey bands); ii) Z-mode (cyan lines); iii) A-mode (red lines). Stick diagrams (on the top; PL and UL are indicated in green and blue, respectively) and APO torques (on the bottom) are shown for the A-mode condition. Pink vertical bands represent the time-intervals corresponding to the enabled assistive torques. (C) The perturbed and unperturbed hip ranges of motion during the no-APO, Z- and A-modes trials (orange, cyan and red bars, respectively) are shown for elderly subjects (mean values ± SD). The label * indicates a significant (p < 0.05) difference among trials. (D) The perturbed and unperturbed hip ranges of motion during the Z- and A-modes trials (cyan and red bars, respectively) are shown for amputee groups (mean values ± SD). The time axes in panels A and B start at the heel strike of the unperturbed gait cycle (grey/shadow area) and at the onset of the perturbed strides (blue and red lines).

Figure 4. Analysis of the stability against fall.

Subplots (A and B) show the COM motion state for one elderly subject and one amputee, during the Z- and A-modes (cyan and red lines, respectively). The green area represents the stability region: forward falls would be initiated if states exceeded the upper boundary; backward falls would be initiated if states dropped below the lower boundary. The two components of the COM motion state (i.e., position and velocity of the COM) were calculated relative to the base of support (BOS) and normalized by foot length and (g*H)^1/2, respectively, where g is gravitational acceleration and H is body height. Two single support phases, concerning the PL and UL, were identified from the lift-off and the touch-down of the unperturbed (I-II events, LO_U and TD_U) and the perturbed (III-IV events, LO_P and TD_P) feet, respectively. The effect of the fall mitigation action was observed during the second single support phase, and, accordingly, the dynamic stability was assessed at the end of the compensatory stride (i.e., IV event). (C) COM stability and (D) margin of stability (MOS) are depicted for the no-APO, Z- and A-modes (orange, cyan and red bars respectively), for both elderly and amputee groups (mean values ± SD). The label * indicates a significant (p < 0.05) difference among trials.