# Self-Predictive Representation for Autonomous UAV Object-Goal Navigation

arXiv: https://arxiv.org/abs/2604.21130 · HTML: https://mlsanity.com/paper/2604.21130/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 19 of 19)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Decoupling Representation Learning from Reinforcement Learning](https://mlsanity.com/paper/2009.08319/) (2020)
- [Self-Supervised Representation Learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2110.09327/) (2021)
- [State Representation Learning for Control: An Overview](https://mlsanity.com/paper/1802.04181/) (2018)
- [Bridging State and History Representations: Understanding Self-Predictive RL](https://mlsanity.com/paper/2401.08898/) (2024)
- [Transferable Representation Learning in Vision-and-Language Navigation](https://mlsanity.com/paper/1908.03409/) (2019)
- [Learning Markov State Abstractions for Deep Reinforcement Learning](https://mlsanity.com/paper/2106.04379/) (2021)
- [Understanding Self-Predictive Learning for Reinforcement Learning](https://mlsanity.com/paper/2212.03319/) (2022)
- [Learning a State Representation and Navigation in Cluttered and Dynamic Environments](https://mlsanity.com/paper/2103.04351/) (2021)
- [Self-supervised Representation Learning with Relative Predictive Coding](https://mlsanity.com/paper/2103.11275/) (2021)
- [Representation Learning for Event-based Visuomotor Policies](https://mlsanity.com/paper/2103.00806/) (2021)
- [Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations](https://mlsanity.com/paper/1909.06993/) (2019)
- [NavRep: Unsupervised Representations for Reinforcement Learning of Robot Navigation in Dynamic Human Environments](https://mlsanity.com/paper/2012.04406/) (2020)
- [ENTL: Embodied Navigation Trajectory Learner](https://mlsanity.com/paper/2304.02639/) (2023)
- [Unmanned Aerial Vehicle for Internet of Everything: Opportunities and Challenges](https://mlsanity.com/paper/2003.13311/) (2020)

## Abstract (arXiv)

Autonomous Unmanned Aerial Vehicles (UAVs) have revolutionized industries through their versatility with applications including aerial surveillance, search and rescue, agriculture, and delivery. Their autonomous capabilities offer unique advantages, such as operating in large open space environments. Reinforcement Learning (RL) empowers UAVs to learn intricate navigation policies, enabling them to optimize flight behavior autonomously. However, one of its main challenge is the inefficiency in using data sample to achieve a good policy. In object-goal navigation (OGN) settings, target recognition arises as an extra challenge. Most UAV-related approaches use relative or absolute coordinates to move from an initial position to a predefined location, rather than to find the target directly. This study addresses the data sample efficiency issue in solving a 3D OGN problem, in addition to, the formalization of the unknown target location setting as a Markov decision process. Experiments are conducted to analyze the interplay of different state representation learning (SRL) methods for perception with a model-free RL algorithm for planning in an autonomous navigation system. The main contribution of this study is the development of the perception module, featuring a novel self-predictive model named AmelPred. Empirical results demonstrate that its stochastic version, AmelPredSto, is the best-performing SRL model when combined with actor-critic RL algorithms. The obtained results show substantial improvement in RL algorithms' efficiency by using AmelPredSto in solving the OGN problem.