Takuya Kiyokawa 교수

To achieve recycling of mixed industrial waste toward an advanced sustainable society, waste sorting automation through robots is crucial and urgent. For this purpose, a robot is required to recognize the category, shape, pose, and condition of different waste items and manipulate them according to the category to be sorted. This survey considers three potential difficulties in the sorting automation: 1) End-effector: to robustly grasp and manipulate different waste items with dirt and deformati

Owing to human labor shortages, the automation of labor-intensive manual waste-sorting is needed. The goal of automating waste-sorting is to replace the human role of robust detection and agile manipulation of waste items with robots. To achieve this, we propose three methods. First, we provide a combined manipulation method using graspless push-and-drop and pick-and-release manipulation. Second, we provide a robotic system that can automatically collect object images to quickly train a deep neu

Automated factories use deep-learning-based vision systems to accurately detect various products. However, training such vision systems requires manual annotation of a significant amount of data to optimize the large number of parameters of the deep convolutional neural networks. Such manual annotation is very time-consuming and laborious. To reduce this burden, we propose a fully automated annotation approach without any manual intervention. To do this, we associate one visual marker with one o

To reduce human intervention in the process of manually teaching assembly sequences to industrial robots, we developed an automated sequence planning method using only a 3D CAD model. In the proposed method, first, to find an assembly sequence for many parts, a genetic algorithm generates the initial chromosome based on interference, rather than merely generating a randomized initial chromosome. Second, to generate an assembly sequence satisfying the preferred insertion condition (e.g. male–fema

To collect a human-annotated dataset for training deep convolutional neural networks is a very time-consuming and laborious process. To reduce this burden, we previously proposed an automated annotation by placing one visual marker above the detection target object in the training phase. However, in this approach, occasionally the marker hides the object surface. To avoid this issue, we propose placing a pedestal with multiple markers at the bottom of the object. If we use multiple markers, the

Aiming to generate easy-to-handle assembly sequences for robotic assembly, this study tackles assembly sequence generation by considering two tradeoff objectives: (1) insertion conditions and (2) degrees of constraints among assembled parts. We propose a multiobjective genetic algorithm to balance these two objectives for generating assembly sequences. Furthermore, the method of extracting part relation matrices including interference-free, insertion, and degree of constraint matrices is extende

To pour various contents from a container, a robot needs to be able to generate a trajectory of its arm, to grasp containers, and to estimate the amount poured. We propose a method only based on tactile sensing to generate the overall pouring motion including all the required abilities. Using a robot arm, we generated a human-like tipping motion and developed a grasping strategy to prevent slippage of the robot's fingertips for objects whose center of gravity changes while pouring. With this met

This study addresses a multi-objective optimization problem in the planning of an uncertainty-aware sequence and motion for mechanical products with intricate structures and numerous contact areas. To generate an optimized sequence and motion that satisfies multiple conditions under mandatory requirements, we use a multi-objective optimization algorithm inspired by Non-Dominated Sorting Genetic Algorithm III, along with contact-rich robotic assembly-oriented constraints and objective functions.

In the disease developing mechanism of baseball elbow, it is believed that there is a need to understand the skeletal system of the elbow joint and forearm. Focusing on the interior of a elbow joint, the humerus, ulna and radius are constituted a complex structure covered with soft tissue, such as the joint capsule and collateral ligaments. In order to clarify the failure of the forearm, Kecskemethy et al., considered a simple forearm skeleton model. Although they estimated ulnar behavior by adj

Through self-supervised learning in simulation, our assumed robotic waste sorter acquires an efficient action policy to scatter densely gathered objects and grasp them. To promptly generalize the model according to the short-life cycle and various-shaped waste items carried in recycling facilities, we are considering quickly reconstructing the simulator used for the training. The simulator requires object models to be reproduced as realistically as possible in appearance and shape. To tackle qui

Mobile grasping enhances manipulation efficiency by utilizing robots’ mobility. This study aims to enable a commercial off-the-shelf robot for mobile grasping, requiring precise timing and pose adjustments. Self-supervised learning can develop a generalizable policy to adjust the robot’s velocity and determine grasp position and orientation based on the target object’s shape and pose. Due to mobile grasping’s complexity, action primitivization and step-by-step learning are crucial to avoid data

This study tasckles the problem of many-objective sequence optimization for semi-automated robotic disassembly operations. To this end, we employ a many-objective genetic algorithm (MaOGA) algorithm inspired by the Non-dominated Sorting Genetic Algorithm (NSGA)-III, along with robotic-disassembly-oriented constraints and objective functions derived from geometrical and robot simulations using 3-dimensional (3D) geometrical information stored in a 3D Computer-Aided Design (CAD) model of the targe

Mobile grasping enhances manipulation efficiency by utilizing robots' mobility. This study aims to enable a commercial off-the-shelf robot for mobile grasping, requiring precise timing and pose adjustments. Self-supervised learning can develop a generalizable policy to adjust the robot's velocity and determine grasp position and orientation based on the target object's shape and pose. Due to mobile grasping's complexity, action primitivization and step-by-step learning are crucial to avoid data