leggedrobotics/elevation_mapping_cupy

Health v2 · maintenance only

Adoption not part of the score

1131 stars · 207 forks observed · 2026-10-20

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A GPU-accelerated elevation mapping library for robotics, built on CuPy and integrated with ROS, that fuses point clouds into multi-modal terrain maps. It provides height drift compensation, raycasting-based artifact removal, and learning-based traversability estimation for legged robot locomotion and navigation.

Use cases

• build elevation maps from lidar or depth point clouds on GPU
• estimate terrain traversability for legged robot path planning
• compensate state estimation drift in robot terrain mapping
• remove mapping artifacts from overhanging obstacles using raycasting
• fuse geometry, semantics, and RGB data into multi-modal elevation maps
• run real-time terrain perception for quadruped locomotion

When to choose

• you need real-time elevation mapping for legged robots or mobile robots
• your ROS pipeline needs GPU-accelerated point cloud registration and raycasting
• you want multi-modal terrain layers like traversability, semantics, or RGB
• you are doing research on rough-terrain locomotion and navigation

When to avoid

• you need mapping on CPU-only hardware without an NVIDIA GPU
• your project does not use ROS or robotics middleware
• you need general-purpose SLAM rather than height-map terrain representation
• you want a plug-and-play mapping solution without robotics integration work

Facets

library · maturity active

computer-vision image-processing machine-learning simulation plugin-system robotics autonomous-vehicles computer-vision machine-learning python elevation-mapping cupy ros legged-robots terrain-perception point-cloud traversability gpu-accelerated linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="leggedrobotics/elevation_mapping_cupy")