Preliminary design of a terrain recognition system

Abstract

This paper aims to design a wearable terrain recognition system, which might assist the control of powered artificial prosthetic legs. A laser distance sensor and inertial measurement unit (IMU) sensors were mounted on human body. These sensors were used to identify the movement state of the user, reconstruct the geometry of the terrain in front of the user while walking, and recognize the type of terrain before the user stepped on it. Different sensor configurations were investigated and compared. The designed system was evaluated on one healthy human subject when walking on an obstacle course in the laboratory environment. The results showed that the reconstructed terrain height demonstrated clearer pattern difference among studied terrains when the laser was placed on the waist than that when the laser was mounted on the shank. The designed system with the laser on the waist accurately recognized 157 out of 160 tested terrain transitions, 300ms–2870ms before the user switched the negotiated terrains. These promising results demonstrated the potential application of the designed terrain recognition system to further improve the control of powered artificial legs.

An automatic and user-driven training method for locomotion mode recognition for artificial leg control

“…1 shows the sensor setup of the terrain detection interface. A portable laser distance sensor and an inertial measurement unit (IMU) are placed on the prosthesis user's waist as suggested in [10], because this sensor configuration has been demonstrated to provide stable signals with very small noises and good performance for recognizing terrain types. Before the training procedure starts, a calibration session is conducted first to measure a few parameters for later use in the training process.…”

Legal and regulatory challenges for physical assistant robots

“…For those obstacles that impede normal gait, several sensors could be added to the device as well as the proposed Terrain Recognition System (TRS) in [32]. But the increase of inputs creates more delay in response timing.…”

Detection of Gait Modes Using an Artificial Neural Network during Walking with a Powered Ankle-Foot Orthosis

“…These schemes were capable of detecting different phases only during level ground walking (Phase 1: stance flexion/extension; Phase 2: preswing; Phase 3: swing flexion; Phase 4: swing extension). Another common approach for gait mode recognition involved using inertial measurement units (IMUs) or other sensors [12–16]. Zhang et al [12] developed an algorithm to predict upcoming terrain height using a large number of sensors (laser sensor and four IMUs).…”

“…Another common approach for gait mode recognition involved using inertial measurement units (IMUs) or other sensors [12–16]. Zhang et al [12] developed an algorithm to predict upcoming terrain height using a large number of sensors (laser sensor and four IMUs). Wang et al [13] also detected the locomotion mode recognition by using similar sensor signals (laser sensor and IMUs).…”

“…In summary, existing gait mode recognition schemes have shortcomings of not being autonomous [4, 5], delay in detection of a new mode until the next step [16, 18], difficulty of implementation in real-time [6–10, 17], dependency on trained stair heights [16], or need for a large number of sensors [12–15, 19, 20]. There are currently no reliable gait mode recognition algorithms available which can detect all of the modes without long delays and without the use of a large number of sensors.…”