26 accepted papers
Autonomous agents capable of diverse object manipulations should be able to acquire a wide range of manipulation skills with high reusability. Although advances in deep learning have made it increasingly feasible to replicate the dexterity of human teleoperation in robots, generalizing these acquire…
In imitation learning for robotic manipulation, decomposing object manipulation tasks into sub-tasks enables the reuse of learned skills and the combination of learned behaviors to perform novel tasks, rather than simply replicating demonstrated motions. Human gaze is closely linked to hand movement
Deep imitation learning is a promising approach in robotic manipulation, enabling robots to acquire versatile and adaptable skills. In such research, by learning various tasks, robots achieved generality across multiple objects. However, such multi-task robot datasets have mainly focused on single-a…
Flexible manipulators have high degrees of freedom and deformability, enabling dexterous movements and allowing for unexpected contacts with the environment. Underactuated tendon-drive mechanisms are the most widely adopted because of their simplicity and effectiveness. However, they suffer from dif
Deep imitation learning is promising for robot manipulation because it only requires demonstration samples. In this study, deep imitation learning is applied to tasks that require force feedback. However, existing demonstration methods have deficiencies; bilateral teleoperation requires a complex co
Tensegrity structures, which are made of struts and tendons, are attracting attention as a platform for adaptive and resilient robots with connections to biological systems. However, they are difficult to control because of their elasticity, deformability, and tight coupling between their elements.
Soft continuum arms have significant potential for use in various applications due to their extremely high degrees of freedom. For example, these soft arms can be used for grasping and manipulating fragile materials in the deep sea or carrying a human to rescue in unstructured environments. However,
Deep imitation learning is a promising approach that does not require hard-coded control rules in autonomous robot manipulation. The current applications of deep imitation learning to robot manipulation have been limited to reactive control based on the states at the current time step. However, futu…
Replacing sensors with indirect sensing techniques contributes to retaining the flexibility of soft robots. By combining physical models with recurrent neural networks (which we term a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"/> <bold xmlns:mml
Imitation learning has attracted attention as a method for realizing complex robot control without programmed robot behavior. Meta-imitation learning has been proposed to solve the high cost of data collection and low generalizability to new tasks that imitation learning suffers from. Meta-imitation…
A high-precision manipulation task, such as needle threading, is challenging. Physiological studies have proposed connecting low-resolution peripheral vision and fast movement to transport the hand into the vicinity of an object, and using high-resolution foveated vision to achieve the accurate homi
This letter focuses on the jump-and-hit motion of a humanoid robot, wherein a robot instantaneously jumps forward and hits a flying ball in the air, similar to how human players behave in volleyball games. We propose a Immediate Motion generation using a Lookup table of learned dynamics (IMoLo) for
Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging. In a dual-arm manipulation setup, the increased number of sta…
Segmentation of a compound task with multiple subtasks is crucial for imitation learning. Conventional unsupervised segmentation methods focused on only reproducibility of demonstrations and did not use the property that goal-directed actions rarely occur without intention. In this paper, we propose…
The need for cable connection with soft robotic systems suppresses the benefits granted by their softness and flexibility. Such systems can be untethered by equipping batteries or by relying on non-electrical actuation mechanisms. However, these approaches cannot simultaneously support long-term and
Spiking neurons might play a larger role than simply as an efficient signal transmitter. Several studies have demonstrated how movements can be generated using networks of spiking neurons. However, the complexity of spiking neural networks makes their implementation difficult, and the use of spiking…
Deep imitation learning enables the learning of complex visuomotor skills from raw pixel inputs. However, this approach suffers from the problem of overfitting to the training images. The neural network can easily be distracted by task-irrelevant objects. In this letter, we use the human gaze measur
Visual occlusions caused by the environment or by the robot itself can be a problem for object recognition during manipulation by a robot hand. Under such conditions, tactile and somatosensory information are useful for object recognition during manipulation. Humans can visualize the appearance of i…
We describe the development of a robot configured to play badminton, a dynamic sport that requires high accuracy. We used pneumatic-electric hybrid actuators, each combining a pneumatic actuator, with high-speed and lightweight attributes, and an electric motor with good controllability. Our first o
It is difficult to design agile soft-bodied robots owing to their inherent softness. To overcome this problem, we propose a structure-integrated bistable module that uses snap-through buckling for agile motions. First, we confirmed that a 0.05-m-long module was able to jump to 0.13 m high. Through i
The dolphin kick is a swimming style characterized by undulation of the body. As a platform for swimming research, we have developed a musculoskeletal humanoid robot called Triton. Triton has a flexible spine with erector spinae muscles and a stiffness adjustment system for lumbar joints. The muscul…
This paper presents novel event-driven forward kinematics algorithms for open kinematic chains with O(log n) complexity. This event-driven algorithm can efficiently update forward kinematics only when new sensory data comes. This will also contribute to localization of computational resources at sen…
Sports, especially badminton, require participants to perform dynamic and skillful motions. Previous robots have had difficulty in performing like a human because of their severe limitations of low operating speed, heavy bodies, and simplistic mechanisms. In this letter, we propose a new robot desig
This paper presents a new algorithm for forward kinematics, called Asynchronous Forward Kinematics (AFK). The algorithm has the complexity of O(log n) for updating one joint angle, and O(logn) for obtaining a homogeneous transformation matrix between links. AFK enables computation for efficient forw…
Systems with changeable mechanical properties show promise for expanding the applications of dynamic robots. We proposed the Torque-Angle Relationship Control System (TARCS) for musculoskeletal robots with changeable output properties. First, we formulated TARCS and examined its static properties. N
The goal of this paper is to develop a regrasp planning algorithm general enough to perform statistical analysis with thousands of experiments and arbitrary mesh models. We focus on pick-and-place regrasp which reorients an object from one placement to another by using a sequence of pick-ups and pla…