MAROKO133 Update ai: Geely unveils in-wheel motors that allow EVs to move sideways with 90

📌 MAROKO133 Breaking ai: Geely unveils in-wheel motors that allow EVs to move side

Chinese automaker Geely is showcasing a new step in vehicle control technology with the unveiling of a self-developed driving unit demonstrated on the EX5 electric crossover prototype. In a recently shared video, the company highlighted a system that integrates electric motors directly into the wheels, enabling far greater flexibility in how the vehicle moves compared to conventional drivetrains.

At the core of this setup is a modular driving unit designed to support advanced maneuvering functions, including precise low-speed movement and unconventional steering angles. During the demonstration, the system was operated using a dedicated control glove, allowing the vehicle to be guided remotely. Geely says this interface is only a transitional solution. 

In future iterations, control is expected to shift to consumer devices such as smartphones or smartwatches, enabling owners to reposition the vehicle remotely and with high precision in confined spaces.

Zero-radius turning with independent wheel motors

In the prototype setup, four independent driving units are mounted directly inside the wheels, each capable of rotating up to 90 degrees. This configuration allows every wheel to steer and drive independently, unlocking a level of maneuverability not possible with conventional layouts. As a result, the Geely EX5 prototype can perform on-the-spot turns, move laterally, and park in extremely tight spaces before exiting them with ease. Both the front and rear axles are able to operate in different directions simultaneously, enabling precise control in confined urban environments.

Beyond tight-space maneuvering, the newly unveiled system also enables a so-called crab driving mode, allowing the vehicle to move laterally without changing its orientation. According to Geely, the wheel-integrated driving unit can also enhance stability in challenging conditions such as slippery surfaces and strong crosswinds by independently controlling each wheel. 

However, there are potential trade-offs with the new design. The rear wheel arches of the Geely EX5 prototype appear to have been enlarged to accommodate rims capable of rotating 90 degrees, which could noticeably reduce interior space. Additionally, the prototype’s windows were covered with black film, and CarNewsChina reports that the rear seats may have been removed entirely, further hinting at compromises made to integrate the advanced wheel-steering system.

EX5 leads company’s new global electric crossover push

The Geely EX5 electric crossover is emerging as a key pillar in the company’s latest strategy to expand its presence in international markets. Designed to combine practicality with advanced technology, the EX5 is equipped with a single electric motor on the front axle that delivers a peak output of 160 kW, providing smooth acceleration, responsive handling, and a comfortable driving experience.

Powering the vehicle is a 60.2 kWh battery, offering a WLTP-certified cruising range of around 267 miles on a full charge, making it suitable for both city commuting and longer trips.

The EX5 also integrates Geely’s latest EV technologies, including advanced driving controls, energy management systems, and safety features, ensuring a balance of efficiency, stability, and performance in diverse driving conditions.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Breaking ai: Which Agent Causes Task Failures and When?Researchers fro

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