UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking

arXiv:2610.00878 · cs.RO, cs.CV, eess.IV · Submitted 2026-10-01 · Read on arXiv

cs.RO, cs.CV, eess.IV

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: The project page is at https://tw5775.github.io/UniTrackPLA

Project page: https://tw5775.github.io/UniTrackPLA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 14× in this paper · explained in 3 episodes
• Action Space — 7× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Panoramic-Aware Encoding — 5× in this paper
• World-Action Consistency — 5× in this paper
• Ablation — 4× in this paper · explained in 1 episode
• Foundation Model — 4× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Foundation Models — 3× in this paper · explained in 7 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Closed-Loop Control — 2× in this paper · explained in 2 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Single-Target Following — 2× in this paper
• Transformer — 2× in this paper · explained in 2 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sim-to-Real Transfer — 1× in this paper · explained in 2 episodes
• VLA Models — 1× in this paper · explained in 3 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation
• ReferTrack: Referring Then Tracking for Embodied Visual Tracking
• P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation
• OmniVLN: Omnidirectional 3D Perception and Token-Efficient LLM Reasoning for Visual-Language Navigation across Air and Ground Platforms
• EAGOR: Embodied Reasoning in Omni-direction
• Hierarchical Instruction-aware Embodied Visual Tracking
• Follow-Bench: A Unified Motion Planning Benchmark for Socially-Aware Robot Person Following
• UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following
• DINOv3
• Qwen3 Technical Report

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
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies