Solvi Arnold

Synchronous dressing support based on working-status prediction

Takahiro Yamazaki, Yutaka Takase, Solvi Arnold, Kimitoshi Yamazaki

This paper describes a method for helping a person dress with the help of a robot. We place strong emphasis on the idea of assisting someone who is acting proactively while considering their work capacity. The present study aims to develop a …

jp (code pays fourni par la source)

Action planning for retrieving one item from a cluster of connected items using affordance-based prediction

Kimitoshi Yamazaki, Solvi Arnold, Naoki Hiratsuka, Kenichi Minoya et autres

This paper describes a method for retrieving a target object to which direct access is blocked by other objects. We specifically consider the case where these objects are physically connected via deformable stems and branches. We highlight the importance of affordance-based prediction …

jp, us (code pays fourni par la source)

A dataset and benchmark for robotic cloth unfolding grasp selection: The ICRA 2024 Cloth Competition

Victor-Louis De Gusseme, Thomas Lips, Remko Proesmans, Julius Hietala et autres

Robotic cloth manipulation suffers from a lack of standardized benchmarks and shared datasets for evaluating and comparing different approaches. To address this, we created a benchmark and organized the ICRA 2024 Cloth Competition, a unique head-to-head evaluation focused on grasp pose selection …

be, kr, si, cn, hk, ae, jp, us, fr (code pays fourni par la source)

How Reward and the Elimination of Dependence Thereon Lead Evolution to High-Bandwidth Learning

Solvi Arnold, Reiji Suzuki, Takaya Arita

Efficient learning is fundamental to intelligence. Popular AI learning methods still fall short of advanced biological learners in terms of efficiency, and hence, in intelligence. Given the inherent trade-off between efficiency and generality, we can understand this low efficiency as the Cost …

jp (code pays fourni par la source)

Reward-Agnostic Learning of Locomotion in Individualised Bodies Using Reward as an Evolutionary Stepping Stone

Solvi Arnold, Reiji Suzuki, Takaya Arita

Efficient learning is a defining feature of biological intelligence that remains difficult to replicate in artificial systems. We recently hypothesised that prior evolution of low-efficiency reward-driven learning can facilitate subsequent evolution of efficient reward-agnostic observation-driven learning for various task domains. However, this …

jp (code pays fourni par la source)

Online Motion Modification for Mobile Manipulators Based on Sequential Quadratic Programming

Kimitoshi Yamazaki, Takuya Iwasaki, Yutaka Takase, Solvi Arnold et autres

This paper describes a method of motion planning for mobile manipulators. The target task is to reach out and grasp an object on a table or a shelf. We especially focus on two things: (i) online motion modification, which is for avoiding …

jp (code pays fourni par la source)

Flow-Lenia.png: Evolving Multi-Scale Complexity by Means of Compression

Tadashi Adachi, Solvi Arnold, Takafumi Mochizuki, Kimitoshi Yamazaki

We propose a fitness measure quantifying multi-scale complexity for cellular automaton states, using compressibility as a proxy for complexity. The use of compressibility is grounded in the concept of Kolmogorov complexity, which defines the complexity of an object by the size of …

Breaching the Bottleneck: Evolutionary Transition from Reward-Driven Learning to Reward-Agnostic Domain-Adapted Learning in Neuromodulated Neural Nets

Solvi Arnold, Reiji Suzuki, Takaya Arita, Kimitoshi Yamazaki

Advanced biological intelligence learns efficiently from an information-rich stream of stimulus information, even when feedback on behaviour quality is sparse or absent. Such learning exploits implicit assumptions about task domains. We refer to such learning as Domain-Adapted Learning (DAL). In contrast, AI …

Wiring connector-terminated cables based on manipulation planning with collision-free EMD net

Kimitoshi Yamazaki, Kyoto Nozaki, Yuichiro Matsuura, Solvi Arnold

In this paper, we propose a manipulation planning method for cable wiring in the assembly of electric appliances etc. We address a scenario where a robot grasps a connector attached to the end of a cable and has to bring the connector …

jp (code pays fourni par la source)

Breaching the Bottleneck: Evolutionary Transition from Reward-Driven Learning to Reward-Agnostic Domain-Adapted Learning in Neuromodulated Neural Nets

Solvi Arnold, Reiji Suzuki, Takaya Arita, Kimitoshi Yamazaki

Advanced biological intelligence learns efficiently from an in-formation-rich stream of stimulus information, even when feed-back on behaviour quality is sparse or absent. Such learning ex-ploits implicit assumptions about task domains. We refer to such learning as Domain-Adapted Learning (DAL). In contrast, AI …

jp (code pays fourni par la source)

A Dual-Arm Manipulation System for Unfolding and Folding Rectangular Cloth

Yusuke Kuribayashi, Yuta Yoshioka, Keisuke Onda, Takahiro Yamazaki et autres

This paper describes a robot system that can perform several cloth manipulation tasks. Many commendable activities on deformable object manipulation are underway in the research community. One such activity is the Cloth Manipulation Track organized as part of the Robotic Grasping and …

jp (code pays fourni par la source)

Action Primitive Classification of Sewing Operations toward Training Unskilled Workers

Akihisa Ishikawa, Naoki Hiratsuka, Yutaka Takase, Solvi Arnold et autres

In this study, we proposed a system for measuring hand posture and fingertip force for training unskilled workers who sew with sewing machines. Furthermore, we classified sewing behaviors by constructing deep learning models using time-series color image data, hand posture, and fingertip …

jp (code pays fourni par la source)