Browsing by Author "Madusanka, DGK"

Now showing 1 - 7 of 7

item: Conference-Abstract
A 3DOF transtibial robotic prosthetic limb
Madusanka, DGK; Wijayasingha, LNS; Sanjeevan, K; Ahamed, MAR; Edirisooriya, JCW; Gopura, RARC
A robotic prosthesis is a device which is used to replace a missing body part. These devices are intended to return the amputees to their pre-amputation functional status. Below knee (Transtibial) amputation is the most common amputation occurred in the lower limb. That is caused by reasons such as diseases, injury due to explosions of anti-personnel land mines and accidents. The existing prostheses for transtibial amputees have yet to be improved to reinstate the biomechanical functions normally provided by the ankle joint. Therefore, the purpose of this research is to develop a transtibial robotic prosthesis which would provide functions usually provided by the ankle. The proposed design consists of 3 Degrees of Freedom (DOF) to generate similar biomechanical motions at the ankle joint. Further it includes a passive regenerative system to reduce motor power requirement of dorsiflexion/plantarflexion. Experiments are carried out to verify the effectiveness of the proposed prosthetic limb and to verify the possibility of using electromyographic (EMG) signal based control of the prosthesis.
item: Thesis-Full-text
Development of a vision aided reach-to-grasp path planning and controlling method for trans-humeral robotic prostheses
Madusanka, DGK; Gopura, RARC; Amarasinghe, YWR; Mann, GKI
This study proposes a reach-to-grasp path planning and controlling method for trans- humeral prostheses. Trans-humeral prostheses are used to replace the missing body part after the loss of upper limb (UL) above elbow. Reach-to-grasp paths refers to the paths taken by the human UL to reach towards an object with the intention of grasping. A trans-humeral prosthesis has been designed and fabricated with 5DOF. A simulation environment has been proposed using the design. Simulation environment consists of a virtual shoulder joint which can be actuated according to a natural human shoulder using an Inertial Measurement Unit (IMU). Prosthesis and the simulation environment has been used to experimentally evaluate the proposed path planning method. A reach-to-grasp path planning method combining Electromyography (EMG) signals and vision signals has been proposed. EMG Based Module (EBM) is capable of con- trolling prosthesis elbow motion e ectively with an accuracy of 92%. Visual Servoing Module (VSM) consists of a 2-1/2D visual servoing system to center the object of in- terest to the hand of the prosthesis and to correct the orientation. An object reaching algorithm has been proposed to reach towards the object. Later, the EBM and the VSM has been fused using an fusion lter. An improvement to the above method has been proposed to make the paths straight. It consists of a path generation module and a path tracking module. Path generation module is capable of generating a path towards the object. The object position is located and a path is generated from the current position of the prosthetic hand to the object position with the aid of vision. Path tracking module takes the prosthetic hand on the generated path considering shoulder motions. Two path tracking methods has been proposed: spatial path following method and Model Predictive Controller (MPC) based path tracking method. Proposed path planning method has been experimentally evaluated.
item: Article-Full-text
Hybrid Vision Based Reach-to-Grasp Task Planning Method for Trans-Humeral Prostheses
(IEEE, 2017) Madusanka, DGK; Gopura, RARC; Amarasinghe, YWR; Mann, GKI
This paper proposes a hybrid vision based reachto- grasp task planning method for trans-humeral prostheses exploiting both vision and Electromyography (EMG) signals. The hybrid method mainly consists of 2-1/2D visual servoing module and EMG based module. The visual servoing intends to align the object on to the center of the palm while correcting its orientation. EMG signals extracted from the remaining muscles of the disabled arm due to amputation are used to control the elbow flexion/extension (FE). While using the 2-1/2D visual servoing module, the object reaching algorithm changes the elbow FE angle to reach the palm towards the object of interest. Initially, the EMG based module controls the elbow FE. Once an object is detected, the EMG signals emanating from the arm muscles generates a reach request. This process then activates the visual servoing module to bring the palm towards the object. Since both EMG based module and the visual servoing module are producing elbow FE angles while reaching towards an object, these two modules are integrated to obtain a resultant angle for elbow FE. Experiments are conducted using a simulation environment and a prosthesis to validate the proposed task planning method. The EMG based module is capable of following the natural elbow FE motion. Moreover, the task planning method is capable of driving the prosthesis towards the object with proper orientation.
item: Conference-Full-text
A Review on Hybrid Myoelectric Control Systems for Upper Limb Prosthesis
(2015-08-03) Madusanka, DGK; Wijayasingha, LNS; Gopura, RARC; Amarasinghe, YWR; Mann, GKI
Prosthesis is a device extension which is used to replace a missing body part. Amputees who lost all or part of the upper limb may use a prosthesis depending on their requirement. Externally powered prosthesis holds an importance since it is capable of imitating natural limb motions. However, the way they are controlled stand way back from the natural limb. Myoelectric control systems which uses electromyographic signals holds an important role in controlling prosthesis. This paper reviews the myoelectric control systems for upper limb prosthesis. At first control methods based only on myoelectric signals are briefly reviewed. The main focus is given to review hybrid myoelectric control systems. Hybrid myoelectric control methods are categorized and each category is compared and reviewed. Finally feasibility of using vision as an added sensor was discussed with examples from literature.
item: Conference-Abstract
A Review on hybrid myoelectric control systems for upper limb prosthesis
Madusanka, DGK; Wijayasingha, LNS; Gopura, RARC; Amarasinghe, YWR; Mann, GKI;
Prosthesis is a device extension which is used to replace a missing body part. Amputees who lost all or part of the upper limb may use a prosthesis depending on their requirement. Externally powered prosthesis holds an importance since it is capable of imitating natural limb motions. However, the way they are controlled stand way back from the natural limb. Myoelectric control systems which uses electromyographic signals holds an important role in controlling prosthesis. This paper reviews the myoelectric control systems for upper limb prosthesis. At first control methods based only on myoelectric signals are briefly reviewed. The main focus is given to review hybrid myoelectric control systems. Hybrid myoelectric control methods are categorized and each category is compared and reviewed. Finally feasibility of using vision as an added sensor was discussed with examples from literature.
item: Conference-Abstract
A Simulation environment for control algorithms of transhumeral prostheses
Madusanka, DGK; Gopura, RARC; Amarasinghe, YWR; Mann, GKI
Transhumeral prosthesis is used to cater upper limb amputees who lost their limb above elbow. In order to restore the functionality of upper limb, researchers are working on developing prosthesis and their controllers. This paper presents a simulation environment which can be used to simulate control algorithms of transhumeral prostheses. It consists of a virtual model of a prosthesis and lost degrees of freedom are modelled as joints in the simulator which can be accessed inside the simulator. Furthermore the shoulder joint is actuated through an inertia measurement unit. Simulations were carried out to verify the effectiveness of the simulator.
item: Conference-Full-text
Vision-emg fusion method for real-time grasping pattern classification system
(IEEE, 2021-07) Perera, DM; Madusanka, DGK; Adhikariwatte, W; Rathnayake, M; Hemachandra, K
Although recently developed Electromyography-based (EMG) prosthetic hands could classify a significant amount of wrist motions, classifying 5-6 grasping patterns in real-time is a challenging task. The collaboration of EMG and vision has addressed this problem to a certain extent but could not achieve significant performance in real-time. In this paper, we propose a fusion method that can improve the real-time prediction accuracy of the EMG system by merging a probability matrix that represents the usage of the six grasping patterns for the targeted object. The YOLO object detection system retrieves a probability matrix of the identified object, and it is used to correct the error in the EMG classification system. The experiments revealed that the optimized ANN model outperformed the KNN, LDA, NB, and DT by achieving the highest mean True Positive Rate (mTPR) of 69.34%(21.54) in real-time for all the six grasping patterns. Furthermore, the proposed feature set (Age, Gender, and Handedness of the user) showed that their influence increases the mTPR of ANN by 16.05%(2.70). The proposed system takes 393.89ms(178.23ms) to produce a prediction. Therefore, the user does not feel a delay between intention and execution. Furthermore, the system facilitates users to use multiple-grasping patterns for an object.