紧凑型AI训练方法减少拥挤环境中的导航冲突

September 16, 2026 Compact AI training method reduces navigation conflicts in crowded environments by Daegu Gyeongbuk Institute of Science and Technology edited by Lisa Lock, reviewed by Robert Egan Lisa Lock Scientific Editor Meet our editorial team Behind our editorial process Robert Egan Senior Editor Meet our editorial team Behind our editorial process Editors' notes This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: fact-checked preprint trusted source proofread The GIST Add as preferred source Overview of the proposed framework. Credit: arXiv (2026). DOI: 10.48550/arxiv.2607.19971 A research team led by Professor Daehee Park of the Department of Electrical Engineering and Computer Science at DGIST, in collaboration with a research team from KAIST, has developed a learning technique that enables a single compact AI model to simultaneously predict the movements of nearby people and plan safe navigation paths for robots while reducing performance degradation in both tasks. The research was presented at the 19th European Conference on Computer Vision (ECCV 2026) held in Malmö, Sweden, Sept. 8–12. The paper is available on the arXiv preprint server. A robot navigating through a crowded environment must simultaneously predict the future trajectories of nearby people and plan a safe path that avoids collisions. Performing these two tasks using separate AI models requires significant computational resources and memory, making deployment on real-world robots challenging. Therefore, a technology that enables a single compact AI model to simultaneously perform both tasks is required. However, when multiple functions are incorporated into a single model, they may rely on overlapping model parameters, causing interference during training and resulting in degraded performance. The research team defined this phenomenon between motion prediction and path planning as "Skill Conflict" and confirmed its effects through experiments. To address this issue, the research team developed Disjoint Parameter Training (DPT), which enables each function to be trained primarily using different parts of the AI model. The team then selected only the parts essential to each function and combined them into a single model, keeping the model compact while allowing the two functions to operate simultaneously without interfering with each other. Performance evaluations using representative datasets in robot motion, such as JRDB and JTA, revealed that the proposed method predicted the movements of nearby people more accurately than existing methods while also reducing robot path errors and the likelihood of collisions. Additional experiments applying the method to autonomous driving AI demonstrated improved performance, confirming its potential for application across various fields of physical AI, including robotics and autonomous driving. "AI that moves through physical environments, such as robots and autonomous driving systems, must make multiple decisions simultaneously with limited computing resources," Park said. "This study addresses the performance degradation that occurs when multiple functions are incorporated into a single compact AI model, and we plan to apply the technology to real-world robots to validate its potential for practical use." Publication details Taewon Seo et al, Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training, arXiv (2026). DOI: 10.48550/arxiv.2607.19971 Journal information: arXiv Key concepts Machine learning methodologiesAI traffic safetyAutonomous robotic locomotion Provided by Daegu Gyeongbuk Institute of Science and Technology Who's behind this story? Lisa Lock BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile → Robert Egan Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile → Citation: Compact AI training method reduces navigation conflicts in crowded environments (2026, September 16) retrieved 16 September 2026 from https://techxplore.com/news/2026-09-compact-ai-method-conflicts-crowded.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only. Improving the autonomous navigation of mobile robots in crowded spaces using people as sensors Nov 2, 2022 Researchers develop an AI model for autonomous driving Sep 12, 2022 Robot navigation improves 30% by mimicking how humans spread and forget information Sep 29, 2025 Researchers design 'socially aware' robots that can anticipate and safely avoid people on the move May 18, 2022 New algorithm helps robots avoid collisions Jul 14, 2023 Future-aware AI doubles robot speed in pick-and-place tasks Jul 28, 2026 Flexible flight corridors let drones navigate cluttered spaces faster and more safely 2 hours ago 'Relax-and-round' method could help grids manage data center power demand 2 hours ago Manuscripts-turned AI agents can now 'talk' to each other and make new discoveries 4 hours ago One material, two transistor types: 'Universal charge injector' points toward densely stacked AI chips 2 hours ago Why colder temps can be better for aircraft deicing systems 3 hours ago Steelmaking waste could store solar energy, with electric arc furnace slag leading early tests 4 hours ago