CMP-IRRT*: A Perception-Assisted Height-Adaptive Planner for Quadruped Robots
We propose a perception-assisted height-adaptive planning framework based on CMP-IRRT, a Channel Mamba PointNet-guided Informed RRT planner.
Key points
- Quadruped robots can traverse low obstacles, but many 2D planning pipelines still model obstacles as binary occupied regions and rely on sampling-based search that can be inefficient under a limited budget.
- Given a calibrated top-view RGB observation, the perception module estimates obstacle regions and converts depth predictions into a ground-relative height map.
- Experiments on 2D planning benchmarks show that CMP-IRRT reduces explored nodes and iterations compared with classical and neural-guided baselines, and a controlled ablation supports the contribution of the Mamba-based guide.
- In constructed traversability-aware scenarios, the proposed planner reduces path length by up to 16.3% when low obstacles are traversable, and a Unitree Go2 demonstration further shows executable bypassing and traversal behaviors.
Sources (1)
- [1]CMP-IRRT*: A Perception-Assisted Height-Adaptive Planner for Quadruped RobotsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:33 PM
We propose a perception-assisted height-adaptive planning framework based on CMP-IRRT*, a Channel Mamba PointNet-guided Informed RRT* planner.
Quadruped robots can traverse low obstacles, but many 2D planning pipelines still model obstacles as binary occupied regions and rely on sampling-based search that can be inefficient under a limited budget.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 7, 2026FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification
- Oct 5, 2026vllm-project/vllm v0.31.0
- Oct 5, 2026TIDES: Implicit Time-Awareness in Selective State Space Models
- Sep 30, 2026huggingface/transformers v5.18.0: Release 5.18.0
- Sep 22, 2026vllm-project/vllm v0.30.0
- Sep 9, 2026vllm-project/vllm v0.29.0