LT-Mem Framework from DGIST Wins Best Paper Award at IROS 2026
- Published
- Source
- leaderobot.com
The LT-Mem framework, developed by the Robotics and Mechatronics Department at DGIST, was awarded the Best Paper Award at IROS 2026. Authored by Yumin Lee, Hyoseok Ju, and Giseop Kim, the framework addresses the challenge of tracking object locations over multiple sessions, specifically in scenarios where robots repeatedly map the same environment.
This research is significant as it tackles the issue of 'temporal amnesia,' where existing systems fail to maintain historical object states during mapping sessions. LT-Mem introduces a novel approach to long-term memory in robotics, allowing for better object recognition and tracking across different mapping rounds, which is crucial for applications in dynamic environments.
Looking ahead, the implications of LT-Mem could reshape how robots interact with their surroundings by improving their memory capabilities. As the APRL lab was established only in December 2024, the rapid development of this framework within a year and nine months highlights the potential for future advancements in robotic memory systems. No further timeline was disclosed at the time of publication.
Original report
IROS 2026 Best Paper Award Goes to Newly Established Lab for Long-Term Memory Framework in Robotics
leaderobot.com · LeaderobotThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
-
1
SRS 2027 – Rome, Jun 23–27, 2027 RobotToday · 11 months from now
- 2
- 3
- 4
- 5
- 6
-
7
RoboDEX 2027 – Tokyo, Feb 17–19, 2027 RobotToday · 1 day ago
- 8
-
9
automatica 2027 – Munich, Jun 22–25, 2027 RobotToday · 1 day ago
- 10
-
11
ACIRS 2027 – Hong Kong, Jul 23–25, 2027 RobotToday · 1 day ago
- 12
Related Suppliers
LT Automation A/S
Denmark
Danish engineering consultancy and systems integrator specializing in collaborative robot automation solutions for SMEs and healthcare.
Wemo Automation AB
Sweden
Varnamo, Sweden injection-molding automation builder founded 1987, now part of Japan's Yushin Group; makes eDesign LT-to-xLine linear robots and grippers.
CushyBots
United States
Wilmington, Delaware maker, founded 2019, of rugged, user-repairable low-cost UGVs for EOD, demining and research, including the R-BOT and CBR-1.
Datatang 数据堂（北京）科技股份有限公司
China
Beijing AI training-data supplier founded 2010 and quoted on NEEQ; its Nexdata arm sells egocentric, teleoperation and hand-pose datasets for robot learning.
Xense Robotics (Qianjue Robotics) 千觉机器人
China
Shanghai startup founded in 2024 by an SJTU tactile-sensing researcher, selling optical tactile sensors and the XTac UMI G1 data-collection gripper.
BIENESIS
France
French agritech startup near Clermont-Ferrand developing a solar-powered, remotely deployable robotic canopy that protects vineyards from frost, hail, and heat.
Living Robot Inc.
Japan
Japanese robotics startup in Date, Fukushima developing AI/5G-enabled service robots including the MANA guide robot and educational walking robots.
Simate
China
Physical AI startup founded in 2026 whose Simate-beta robot model topped the RoboDojo leaderboard; also builds the Sinfra training platform.
Privateer Space
United States
Space domain awareness company providing space object tracking and collision avoidance analytics.
Et Cetera Robotics
United States
Seattle startup developing neuromorphic event-camera software for drone tracking and counter-UAS situational awareness in low-light environments.
Mind with Heart Robotics 深圳无芯科技有限公司
China
Shenzhen maker of biomimetic companion robots, founded 2021; its AnAn AI panda for elderly care was a CES 2026 Innovation Awards honoree.
Shenzhen Honghuo Intelligent Technology Co., Ltd. 深圳市鸿火智能科技有限公司
China
SoulX is a Shenzhen startup making MoYa, a consumer-grade pneumatic soft robot companion designed for sleep soothing and emotional well-being.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
