Automated Apple Picking Robot
Across the world, the costs of labour are increasing while those for robotic systems are reducing. Apple orchards require a great deal of maintenance throughout the year, including harvesting tasks.
Deep-Learning-Based Apple Recognition and Positioning
Detection and positioning of the fruits is the first step in autonomous harvesting. Locating the fruit at outdoor light is a challenge for the vision system, especially the active systems. Passive vision systems, however, require extra matching algorithms which increase the detection errors. Judging whether a target fruit is pickable or not is highly depends on manipulator and environment, which is also under intensive research.
Scissor Translational Parallel Manipulator (STPM)
Translational Parallel Manipulators (TPM) have platforms that are constrained to not rotate and have high speeds and accuracies, making them useful for 3d printing, manufacturing, assembly and logistic applications. However, the structure of parallel mechanisms results in all arms connecting to a single platform which greatly reduces the workspace of the mechanism.
Biped Robot Control Based on Reinforcement Learning
Reinforcement Learning (RL) is recently introduced to biped robot control for improved balancing performance against complex external disturbances that cannot be modelled. Existing model-based RL and model-free RL approaches are both demanding in computational resources and are of low computational efficiency when handling high-degree-of-freedom biped robots.
Deep-Learning-Based Prostate Cancer Detection
3Accurate detection of cancer region from the MRI/ultrasound images and segmentation of the prostate contour is critical for the diagnosis of prostate cancer. However, the process is very demanding on the urologist’s expertise. An autonomous image processing technique is desired to promote the diagnosis and thus the treatment outcomes.
Reconfigurable Spherical Motion Generator (RSMG)
Flight simulators offer a risk-free and low-cost approach for training pilots. One major challenge of the existing motion bases of the flight simulators is the limited range of motion, which compromises the fidelity of the simulators and consequently the training outcomes.
Monash Epicyclic Parallel Manipulator (MEPaM)
Haptic feedback is critical for precise remote operation of robotic systems as well as human-machine interaction in the virtual environment. Existing six-degree-of-freedom six-legged parallel haptic devices offer limited workspace and low transparency.
Path Planning of Parallel Manipulators
Path planning for parallel manipulators, especially for manipulators greater than three degrees of freedom (DOF) is a challenging task for many reasons. Due to the complicated nature of their kinematics and the dangerous eﬀects of parallel singularities, path planning of these manipulators can be computationally expensive and often the side-eﬀect is that the overall reachable workspace is constrained to a very small operational area.
Robotic Knee Exoskeleton for Rehabilitation
Musculoskeletal disorders and orthopaedic injuries on the knee joint is common. Knee exoskeletons can assist patients with weakened knee muscles in daily activities. Current passive and quasi-passive exoskeletons are limited in certain activities due to the characteristic of the mechanism. The versatility of the device needs to be improved to be more practical.
Adaptive Fruit Gripper
With automation increasing all industries, the need for new adaptive grippers for the use in complex and dynamic environments is increasing. Handling fruit can be a complicated task due to the natural variations in shape and size of each fruit, in addition for the task of automated harvesting the complexity of the task and potential for error is increased.
Power Flow Analysis of Epicyclic Gear Transmission
Epicyclic gear transmissions are widely used in various industrial applications including robotic arms, hybrid vehicle power transmissions and turbine generators. Analysing and enhancing the operational efficiency of gear transmissions are important to design optimisation and control.
In-Bore MRI-Guided Prostate Biopsy Robot
Prostate cancer is one of the most common cancers in men and biopsy is the gold standard for prostate cancer diagnosis. Existing ultrasound-guided biopsy procedures suffer inaccuracy due to the need for image fusion and target projection.
Robotic Hand Prostheses
Hand loss leads to a significant reduction in functionality and psychological issues, which could be compensated by hand prostheses. Existing hand prostheses suffer high patient rejection rate due to lack in functionality (grasping force and control), aesthetic appearance and the ability to produce anthropomorphic motion.
Medical Robot with Remote Centre of Motion (RCM) Mechanism
6Remote centre of motion (RCM) robots are constrained to rotate around a spatial point, making them ideal for robotic minimally invasive surgery for the fixture of incision ports and promotion of patient safety. Yet, existing RCM mechanisms have large device footprints, thus suﬀer extensive collisions when manipulated within conﬁned workspaces near the incision ports.
Robotic Transverse Profiler (RTP)
Profiling the surface is a crucial process in studying the material property of a road pavement. Accurate profiling is time-consuming and labour intensive in the preparation, setup and operation of all the relevant equipment.