Brain-inspired multimodal hybrid neural network for robot place recognition

计算机科学 机器人 人工智能 人工神经网络 人机交互
作者
Fangwen Yu,Yujie Wu,Songchen Ma,Mingkun Xu,Hongyi Li,Huanyu Qu,Chenhang Song,Taoyi Wang,Rong Zhao,Luping Shi
出处
期刊:Science robotics [American Association for the Advancement of Science]
卷期号:8 (78) 被引量:42
标识
DOI:10.1126/scirobotics.abm6996
摘要

Place recognition is an essential spatial intelligence capability for robots to understand and navigate the world. However, recognizing places in natural environments remains a challenging task for robots because of resource limitations and changing environments. In contrast, humans and animals can robustly and efficiently recognize hundreds of thousands of places in different conditions. Here, we report a brain-inspired general place recognition system, dubbed NeuroGPR, that enables robots to recognize places by mimicking the neural mechanism of multimodal sensing, encoding, and computing through a continuum of space and time. Our system consists of a multimodal hybrid neural network (MHNN) that encodes and integrates multimodal cues from both conventional and neuromorphic sensors. Specifically, to encode different sensory cues, we built various neural networks of spatial view cells, place cells, head direction cells, and time cells. To integrate these cues, we designed a multiscale liquid state machine that can process and fuse multimodal information effectively and asynchronously using diverse neuronal dynamics and bioinspired inhibitory circuits. We deployed the MHNN on Tianjic, a hybrid neuromorphic chip, and integrated it into a quadruped robot. Our results show that NeuroGPR achieves better performance compared with conventional and existing biologically inspired approaches, exhibiting robustness to diverse environmental uncertainty, including perceptual aliasing, motion blur, light, or weather changes. Running NeuroGPR as an overall multi–neural network workload on Tianjic showcases its advantages with 10.5 times lower latency and 43.6% lower power consumption than the commonly used mobile robot processor Jetson Xavier NX.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Moonlover发布了新的文献求助10
刚刚
Yelanjiao发布了新的文献求助10
1秒前
冥灵花火完成签到,获得积分10
1秒前
阿阳不想跑坡完成签到 ,获得积分10
2秒前
3秒前
4秒前
慕青应助司空豁采纳,获得10
5秒前
5秒前
忧心的若云完成签到,获得积分10
6秒前
Two-Capitals发布了新的文献求助10
8秒前
迫切发布了新的文献求助10
8秒前
共享精神应助科研小鱼采纳,获得10
9秒前
季不住完成签到,获得积分10
9秒前
陈秋发布了新的文献求助10
10秒前
11秒前
威武青亦完成签到,获得积分10
12秒前
zheng完成签到 ,获得积分10
12秒前
山山而川应助科研通管家采纳,获得10
14秒前
山山而川应助科研通管家采纳,获得10
14秒前
pcr163应助科研通管家采纳,获得80
14秒前
JamesPei应助科研通管家采纳,获得10
14秒前
赘婿应助科研通管家采纳,获得10
14秒前
Lucas应助科研通管家采纳,获得10
14秒前
桐桐应助科研通管家采纳,获得10
14秒前
隐形曼青应助科研通管家采纳,获得10
14秒前
orixero应助科研通管家采纳,获得10
14秒前
Orange应助科研通管家采纳,获得10
14秒前
艾米修兔完成签到,获得积分10
14秒前
小蘑菇应助科研通管家采纳,获得10
14秒前
15秒前
15秒前
16秒前
不想看文献完成签到 ,获得积分10
16秒前
王玄琳发布了新的文献求助10
16秒前
领导范儿应助小博士328采纳,获得10
16秒前
深情安青应助lgyfjl采纳,获得10
17秒前
明理以南完成签到,获得积分10
17秒前
dolesy完成签到,获得积分10
19秒前
aurora完成签到,获得积分10
20秒前
文明8完成签到,获得积分10
20秒前
高分求助中
生物降解型栓塞微球市场(按产品类型、应用和最终用户)- 2030 年全球预测 1000
Statistical Analysis of fMRI Data, second edition (Mit Press) 2nd ed 500
Lidocaine regional block in the treatment of acute gouty arthritis of the foot 400
Ecological and Human Health Impacts of Contaminated Food and Environments 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
International Relations at LSE: A History of 75 Years 308
Italian Feminism of Sexual Difference: A Different Ecofeminist Thought 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3934104
求助须知:如何正确求助?哪些是违规求助? 3479429
关于积分的说明 11004616
捐赠科研通 3209282
什么是DOI,文献DOI怎么找? 1773535
邀请新用户注册赠送积分活动 860484
科研通“疑难数据库(出版商)”最低求助积分说明 797689