MAROKO133 Eksklusif ai: China’s soft bending sensor gives humanoid robot hand sense of its

📌 MAROKO133 Update ai: China’s soft bending sensor gives humanoid robot hand sense

Researchers in China have demonstrated a humanoid dexterous hand that gives robot fingers a reliable sense of their own posture during complex motion.

The research team embedded a new omnidirectional soft bending sensor into the hand. The team enabled real-time perception of both flexion and side-to-side movement in delicate manipulation tasks.

Developed by researchers from Zhejiang University, Hangzhou Dianzi University, and Lishui University, the hand features 18 active degrees of freedom and five rigid-flexible fingers.

Soft optical sensor

Each finger integrates a soft optical sensor built from segmented PMMA (polymethylmethacrylate) fibers, a trichromatic LED, and a chromatic detector.

The design works by tracking how red, green, and blue light attenuate differently as the sensor bends. Because the fiber layout separates responses to pitch and yaw, the system can decouple the two motions instead of mixing them together. The paper reports strong repeatability over 100 cycles, with RMSE values of 2.1%, 1.9%, and 3.2% across the three optical channels, according to a press release.

Published in Microsystems and Nanoengineering, the study presents the development of a novel omnidirectional soft bending sensor tailored for humanoid dexterous hands to facilitate posture perception in delicate manipulation tasks. Drawing inspiration from the human hand’s intricate design and proprioceptive capabilities, this study aims to enhance the dexterity of robotic hands, particularly in multi-degree-of-freedom (DoF) motion and posture perception.

Sensor demonstrated excellent stability in challenging tasks

Researchers revealed that the sensor demonstrated excellent measurement performance, stability, and repeatability in challenging tasks such as using scissors, operating a computer mouse, and playing the piano. This technology addresses the challenges associated with multi-DoF motion and omnidirectional posture perception in robotic hands, according to researchers.

The team also highlighted that the technology enhances robotic hands’ capabilities in delicate manipulation tasks and paving the way for further advancements in humanoid dexterous hand development.

One of the most important advantages of this soft sensor is its ability to provide detailed and real-time feedback. Because it can detect multiple forms of mechanical interaction—such as pressure, strain, and bending—it gives robots a more nuanced sense of touch compared to earlier systems. This is particularly useful in tasks that require precision.

The potential applications of this technology are broad and impactful. In robotics, it can enable machines to perform complex manipulation tasks with greater care and accuracy. In the field of prosthetics, such sensors could help create artificial limbs that provide users with a more natural sense of touch, improving control and comfort.

Additionally, the technology could be used in healthcare devices for monitoring movement or assisting in rehabilitation. Although the system is still being refined, including improvements in durability and data processing, it represents a major step toward integrating advanced tactile sensing into intelligent machines.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Update ai: Which Agent Causes Task Failures and When?Researchers from

Share My Research is Synced’s column that welcomes scholars to share their own research breakthroughs with over 1.5M global AI enthusiasts. Beyond technological advances, Share My Research also calls for interesting stories behind the research and exciting research ideas. Contact us: [email protected]

Meet the authors
Institutions: Penn State University, Duke University, Google DeepMind, University of Washington, Meta, Nanyang Technological University, and Oregon State University. The co-first authors are Shaokun Zhang of Penn State University and Ming Yin of Duke University.

In recent years, LLM Multi-Agent systems have garnered widespread attention for their collaborative approach to solving complex problems. However, it’s a common scenario for these systems to fail at a task despite a flurry of activity. This leaves developers with a critical question: which agent, at what point, was responsible for the failure? Sifting through vast interaction logs to pinpoint the root cause feels like finding a needle in a haystack—a time-consuming and labor-intensive effort.
 
This is a familiar frustration for developers. In increasingly complex Multi-Agent systems, failures are not only common but also incredibly difficult to diagnose due to the autonomous nature of agent collaboration and long information chains. Without a way to quickly identify the source of a failure, system iteration and optimization grind to a halt.
 
To address this challenge, researchers from Penn State University and Duke University, in collaboration with institutions including Google DeepMind, have introduced the novel research problem of “Automated Failure Attribution.” They have constructed the first benchmark dataset for this task, Who&When, and have developed and evaluated several automated attribution methods. This work not only highlights the complexity of the task but also paves a new path toward enhancing the reliability of LLM Multi-Agent systems.

The paper has been accepted as a Spotlight presentation at the top-tier machine learning conference, ICML 2025, and the code and dataset are now fully open-source.

Paper：https://arxiv.org/pdf/2505.00212
Code：https://github.com/mingyin1/Agents_Failure_Attribution
Dataset：https://huggingface.co/datasets/Kevin355/Who_and_When
 
 
Research Background and Challenges
LLM-driven Multi-Agent systems have demonstrated immense potential across many domains. However, these systems are fragile; errors by a single agent, misunderstandings between agents, or mistakes in information transmission can lead to the failure of the entire task.

Currently, when a system fails, developers are often left with manual and inefficient methods for debugging:
Manual Log Archaeology : Developers must manually review lengthy interaction logs to find the source of the problem.
Reliance on Expertise : The debugging process is highly dependent on the developer’s deep understanding of the system and the task at hand.
 
This “needle in a haystack” approach to debugging is not only inefficient but also severely hinders rapid system iteration and the improvement of system reliability. There is an urgent need for an automated, systematic method to pinpoint the cause of failures, effectively bridging the gap between “evaluation results” and “system improvement.”

Core Contributions
This paper makes several groundbreaking contributions to address the challenges above:
1. Defining a New Problem: The paper is the first to formalize “automated failure attribution” as a specific research task. This task is defined by identifying the failure-responsible agent and the decisive error step that led to the task’s failure.
2. Constructing the First Benchmark Dataset: Who&When : This dataset includes a wide range of failure logs collected from 127 LLM Multi-Agent systems, which were either algorithmically generated or hand-crafted by experts to ensure realism and diversity. Each failure log is accompanied by fine-grained human annotations for:
Who: The agent responsible for the failure.
When: The specific interaction step where the decisive error occurred.
Why: A natural language explanation of the cause of the failure.

3. Exploring Initial “Automated Attribution” Methods : Using the Who&When dataset, the paper designs and assesses three distinct methods for automated failure attribution:
– All-at-Once: This method provides the LLM with the user query and the complete failure log, asking it to identify the responsible agent and the decisive error step in a single pass. While cost-effective, it may struggle to pinpoint precise errors in long contexts.
– Step-by-Step: This approach mimics manual debugging by having the LLM review the interaction log sequentially, making a judgment at each step until the error is found. It is more precise at locating the error step but incurs higher costs and risks accumulating errors.
– Binary Search: A compromise between the first two methods, this strategy repeatedly divides the log in half, using the LLM to determine which segment contains the error. It then recursively searches the identified segment, offering a balance of cost and performance.

Experimental Results and Key Findings 
Experiments were conducted in two settings: one where the LLM knows the ground truth answer to the problem the Multi-Agent system is trying to solve (With Ground Truth) and one where it does not (Without Ground Truth). The primary model used was GPT-4o, though other models were also tested. The systematic evaluation of these methods on the Who&When dataset yielded several important insights:
– A Long Way to Go: Current methods are far from perfect. Even the best-performing single method achieved an accuracy of only about 53.5% in identifying the responsible agent and a mere 14.2% in pinpointing the exact error step. Some methods performed even worse than random guessing, underscoring the difficulty of the task.
– No “All-in-One” Solution: Different methods excel at different aspects of the problem. The All-at-Once method is better at identifying “Who,” while the Step-by-Step method is more effective at determining “When.” The Binary Search method provides a middle-ground performance.
 

– Hybrid Approaches Show Promise but at a High Cost: The researchers found that combining different methods, such as using the All-at-Once approach to identify a potential agent and then applying the Step-by-Step method to find the error, can improve overall performance. However, this comes with a significant increase in computational cost.

– State-of-the-Art Models Struggle: Surprisingly, even the most advanced reasoning models, like OpenAI o1 and DeepSeek R1, find this task challenging.- This h…

Konten dipersingkat otomatis.

🔗 Sumber: syncedreview.com