Unverified50% confidenceFactExact time
VSLAM enables robots to simultaneously localize themselves and construct a map of an unknown environment using only visual sensors, with notable representatives including open-source frameworks such as the ORB-SLAM series, VINS-Mono, and LSD-SLAM.
1
Sources
50%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMatic采用视觉（vSLAM）导航方案，利用摄像头阵列感知环境，配合深度学习模型识别障碍，技术路线与特斯拉自动驾驶的纯视觉理念相近67% similarUnverifiedThe Spot robot combines stereo camera, IMU, and joint encoder data to implement Visual-Inertial Odometry (VIO) for real-time three-dimensional map construction.64% similarUnverified视觉AI涵盖目标检测、图像分割、OCR、视频分析等核心技术，典型技术栈包括PyTorch/TensorFlow、OpenCV以及ONNX/TensorRT等推理优化工具63% similarUnverifiedVLM连接层设计包括线性投影、MLP投影器、交叉注意力（如Flamingo的Perceiver Resampler）或Q-Former（如BLIP-2）62% similarUnverifiedLeRobot 3D provides a camera-to-robot calibration workflow in which users first complete an initial manual alignment and then the system uses a multi-scale ICP algorithm to register the point cloud with the robot's URDF mesh model to optimize extrinsic parameters.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/821081API
curl https://kongchang.com/api/v1/knowledge/claims/821081MCP
get_claim(id=821081)