9 accepted papers
This paper presents a novel hydraulic-driven two- finger robotic gripper designed to handle objects of various shapes and sizes. To meet the demands of field robotics and heavy industrial environments, a self-adaptive finger mechanism was integrated with hydraulic actuation. However, this integratio…
This paper presents a novel hydraulic-driven twofinger robotic gripper designed to handle objects of various shapes and sizes. To meet the demands of field robotics and heavy industrial environments, a self-adaptive finger mechanism was integrated with hydraulic actuation. However, this integration
The successful adaptation of multilingual language models (LMs) to a specific language-task pair critically depends on the availability of data tailored for that condition. While cross-lingual transfer (XLT) methods have contributed to addressing this data scarcity problem, there still exists ongoin…
This letter proposes a multi-degrees-of-freedom two-wheeled inverted pendulum robot (mD-TWIPR) for off-road transportation. A two-wheeled inverted pendulum robot (TWIPR), popularly known as a segway, has high mobility owing to its simple structure without steering or suspension. The proposed robot h
This letter introduces a “rigidable exosuit” inspired by bow mechanics, which can dynamically alter its frame rigidity based on the tension of the attached string. The exosuit affords posture assistance (rigid phase) or unrestricted movement (flexible phase) as required by tasks. In the flexible pha
Cross-lingual transfer (XLT) is an emergent ability of multilingual language models that preserves their performance on a task to a significant extent when evaluated in languages that were not included in the fine-tuning process. While English, due to its widespread usage, is typically regarded as t…
Improving generalization in text-based games serves as a useful stepping-stone towards reinforcement learning (RL) agents with generic linguistic ability. Data augmentation for generalization in RL has shown to be very successful in classic control and visual tasks, but there is no prior work for te…
The Situated Interactive Multi-Modal Conversations (SIMMC) 2.0 aims to create virtual shopping assistants that can accept complex multi-modal inputs, i.e. visual appearances of objects and user utterances. It consists of four subtasks, multi-modal disambiguation (MM-Disamb), multi-modal coreference…
This letter presents a gripper module for a snake-like robot to perform search and rescue tasks in a narrow space. The proposed gripper module has three features: (1) It can accommodate the fingers inside its body. (2) It has three fingers that can grip objects with irregular surfaces stably. (3) On