# Deep-PANTHER: Learning-Based Perception-Aware Trajectory Planner in Dynamic Environments

arXiv: https://arxiv.org/abs/2209.01268 · HTML: https://mlsanity.com/paper/2209.01268/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2022.

## Built on by (most cited first, 11 of 11)

- [CGD: Constraint-Guided Diffusion Policies for UAV Trajectory Planning](https://mlsanity.com/paper/2405.01758/) (2024)
- [RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation](https://mlsanity.com/paper/2502.02054/) (2025)
- [Optimizing Active Perception for Learning Simultaneous Viewpoint Selection and Manipulation with Diffusion Policy](https://mlsanity.com/paper/2409.14615/) (2024)
- [Generative AI for Autonomous Driving: A Review](https://mlsanity.com/paper/2505.15863/) (2025)
- [Towards Task-Oriented Flying: Framework, Infrastructure, and Principles](https://mlsanity.com/paper/2504.15129/) (2025)
- [Learning to Initialize Trajectory Optimization for Vision-Based Autonomous Flight in Unknown Environments](https://mlsanity.com/paper/2309.10683/) (2023)
- [PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner](https://mlsanity.com/paper/2406.10060/) (2024)
- [Dual Agent Learning Based Aerial Trajectory Tracking](https://mlsanity.com/paper/2410.23571/) (2024)
- [Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learning](https://mlsanity.com/paper/2605.28372/) (2026)
- [Anticipatory Risk-Guided Reinforcement Learning for Safe Flight Through Dynamic Clutter](https://mlsanity.com/paper/2607.23565/) (2026)
- [PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability](https://mlsanity.com/paper/2608.14082/) (2026)

## Abstract (arXiv)

This paper presents Deep-PANTHER, a learning-based perception-aware trajectory planner for unmanned aerial vehicles (UAVs) in dynamic environments. Given the current state of the UAV, and the predicted trajectory and size of the obstacle, Deep-PANTHER generates multiple trajectories to avoid a dynamic obstacle while simultaneously maximizing its presence in the field of view (FOV) of the onboard camera. To obtain a computationally tractable real-time solution, imitation learning is leveraged to train a Deep-PANTHER policy using demonstrations provided by a multimodal optimization-based expert. Extensive simulations show replanning times that are two orders of magnitude faster than the optimization-based expert, while achieving a similar cost. By ensuring that each expert trajectory is assigned to one distinct student trajectory in the loss function, Deep-PANTHER can also capture the multimodality of the problem and achieve a mean squared error (MSE) loss with respect to the expert that is up to 18 times smaller than state-of-the-art (Relaxed) Winner-Takes-All approaches. Deep-PANTHER is also shown to generalize well to obstacle trajectories that differ from the ones used in training.