研究了1933篇IROS 论文,我们看到了机器人学的六项新变化
Quick Answer
IROS 2026 reveals that AI has not replaced traditional robotics but has integrated deeply, with 1933 papers highlighting advancements in Robot Learning, Navigation, and Manipulation.
Quick Take
Key findings show that AI models like GeoVLA and DexTact are enhancing traditional robotics by incorporating 3D geometry and tactile feedback, indicating a shift towards complex system integration rather than simple model scaling.
Key Points
- 809 papers focus on Robot Learning, showcasing its prominence in robotics research.
- GeoVLA integrates 3D geometry into VLA models to improve robotic action generation.
- DexTact combines visual and tactile feedback for enhanced dexterous grasping.
- Research indicates a shift towards system engineering for VLA integration in robotics.
- New papers emphasize the need for reasoning and memory in long-term robotic tasks.
DeepSignal Analysis
What happened
The IROS 2026 conference will showcase 1933 papers, highlighting significant advancements in robotics, particularly in areas like Robot Learning, Navigation, and Manipulation. Notably, AI models are being integrated into traditional robotics rather than replacing them, indicating a trend towards complex system integration.
Key evidence
- Of the 1933 papers presented at IROS 2026, approximately 809 focus on Robot Learning and Embodied AI, while 564 address Navigation and Planning.
- Research indicates that AI models like GeoVLA and DexTact are enhancing traditional robotics by incorporating 3D geometry and tactile feedback.
- The integration of AI into robotics is not leading to a simplification of the field, but rather a deeper embedding of learning, perception, planning, control, and manipulation.
Why it matters
The findings from IROS 2026 suggest that the robotics field is evolving to incorporate AI in a way that enhances traditional methodologies. This integration may lead to more sophisticated robotic systems capable of operating in complex environments, which is crucial for future applications in various industries.
What to watch
📖 Reader Mode
~8 min read
作者丨马晓宁
编辑丨岑 峰

01
AI 没有取代传统机器人学,
而是在重新嵌进去

02
VLA 从“证明能做”进入“补短板”阶段

03
机器人正在重新长出“中间层”

04
Manipulation
成为具身智能最密集的战场之一

05
Humanoid 从“会走”向“边走边干活”扩展

06
World Model 很热,但还没有成为主流

07
机器人进入“系统问题时代”
为了方便大家抱团交流、互通会议消息,我们专门建了 IROS 2026 参会交流群!进群你会解锁这些「福利」?
会议情报站:投稿 DDL、格式规范、评审进度……关键节点第一时间送达,再也不怕错过 deadline,投稿准备稳稳的。
同行茶话会:天南海北的同行都在群里,聊心得、碰思路、攒人脉,科研路上我们同行。
前沿补给站:最新研究成果、热点方向实时同步,结合会议主题帮你捋清投稿脉络,给论文灵感加满油。
现场后援团:(会议期间专属开启):到了会场也不用慌——
路线导航:场馆分布、报告厅怎么走,群里随时问;
议题共读:热门 session、Keynote 探讨,错过也能追;
Poster 汇编:现场海报精华整理,一键收藏不遗漏;
约局广场:约饭局、采访局、交流局……想唠嗑、想合作、想面基,群里发起就成。
? 进群传送门: 扫码进群或添加微信Luyoyo_2026,备注:ECCV + 单位/学校+姓名+方向。

搞科研/搞技术,信息差很重要。
来,一起快人一步!

上车,带你看遍全球 AI 顶会精华
可独家畅览:
专家演讲PPT
大会报告全文
热门论文解读
学术新星访谈

扫描上方二维码
或点击「阅读原文」关注雷峰网(公众号:雷峰网)专区。
— Originally published at m.leiphone.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from WebSearch (Tavily)
See more →全球AI芯片峰会,9月上海见!
The 2026 Global AI Chip Summit will take place in Shanghai on September 22-23, focusing on the evolving AI chip landscape, including the shift from training to inference, the rise of diverse chip technologies, and the restructuring of industry competition. Notable speakers include experts from leading universities and companies, discussing advancements in AI chip architecture and applications.