SABER: Learning Attention-based Semantic Affordance for Legged Locomotion
cs.RO
Submitted: 2026-09-18
Updated: 2026-10-02
Terminology
Sources
- Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
- Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
- Advances, challenges, and opportunities for legged robots
- Watch Your Step: Learning Semantically-Guided Locomotion in Cluttered Environment
- AME-2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding
- TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
- Body Transformer: Leveraging Robot Embodiment for Policy Learning
- Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
- LocoVLM: Grounding Vision and Language for Adapting Versatile Legged Locomotion Policies
- QuadPiPS: A Perception-informed Footstep Planner for Quadrupeds With Semantic Affordance Prediction
- Proximal Policy Optimization Algorithms
- mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning
- Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving