16 accepted papers
Quantization techniques such as BitsAndBytes, AWQ, and GPTQ are widely used as a standard method in deploying large language models but often degrades accuracy when using low-bit representations, e.g., 4 bits. Low-rank correction methods (e.g., LQER, QERA, ASER) has been proposed to mitigate this is…
In this letter, we present an autonomous navigation system for goal-driven exploration of unknown environments through deep reinforcement learning (DRL). Points of interest (POI) for possible navigation directions are obtained from the environment and an optimal waypoint is selected, based on the av
For robotic grasping tasks with diverse target objects, some deep learning-based methods have achieved state-of-the-art results using direct visual input. In contrast, actor-critic deep reinforcement learning (RL) methods typically perform very poorly when applied to grasp diverse objects, especiall…
In this study, we present a method to grasp diverse unseen real-world objects using an off-policy actor-critic deep reinforcement learning (RL) with the help of a simulation and the use of as little real-world data as possible. Actor-critic deep RL is unstable and difficult to tune when a raw image…
This paper presents a 3-DOF linkage-driven underactuated finger for achieving several different grasp modes. This finger mechanism is constructed by stacking one five-bar mechanism over one double parallelogram. This special architecture allows for installing all of the actuators on the base. A 2-fi…
In this study, we aim at grasping a single target object in a cluttered environment using a robotic arm. While dexterous grasp for various shapes of objects is not considered in this work, we focus on developing the method to mitigate clutter near the target object as soon as quickly. For this purpo…
We propose a method to generate an order for learning and transferring motor skills based on motion complexity, then evaluate the order to learn motor skills of a task and transfer them to another task as a form of reinforcement learning (RL). Here, motion complexity refers to the complexity calcula
In this paper, we propose a method to model social interaction between a human and a virtual avatar. To this end, two human performers fist perform social interactions according to the Learning from Demonstration paradigm. Then, the relative relevance of all joints of both performers should be reaso…
Feature-based image retrieval and feature matching have been used together in many applications, but they have been treated as two separate problems. We propose an unified approach which, for a query image, finds a set of candidate images together with feature matching results. By considering the lo…
We propose a topology-based Bayesian visual navigation framework, with which we represent the world environment as a collection of scenes. The proposed topological map consists of nodes represented as a bag of visual line words and edges represented as both an adjacency list and relative motion info…
In this paper, we propose a scene clustering algorithm which uses straight line features. Scenes are represented as nodes in the graph, and each connectivity between nodes is calculated by a pre-trained vocabulary tree. By applying a spectral clustering algorithm to the constructed graph, the scenes…
In this paper, we propose a keyframe-based online object learning and detection method. To manage appearance changes of target objects, the proposed method incrementally updates an object database using detection results. One of the major problems in updating the appearance model is that the object…
This paper proposes a passivity-based nonlinear disturbance observer (DOB) design for a powered upper-limb robot control. The proposed DOB allows for the nonlinearities of the robot dynamics, whereas the typical DOB designs cannot. Moreover, by virtue of the passivity property, human operator and en
We present a real-time framework for planning natural and smooth grasping motions in an online manner based on the interaction with human. The proposed framework is able to change its grasp strategies agilely according to the interaction with human. Given human demonstrations, we develop a motion fi…
Dynamic motion of human shows kinematic aspects related to storing elastic energy in skeletal muscle. This results from joint stiffness modulation and as a consequence, countermovement which is opposite to the intended motion is observed. We propose a segmentation algorithm based on a hidden semi-Ma…
In this paper, we propose a novel online multiobject learning and detection algorithm. From single seed images of the target objects, our algorithm detects these objects in the input sequence, and incrementally updates the databases with the detection results. Reasonably sized databases are maintain…