# Active Classification of Moving Targets with Learned Control Policies

arXiv: https://arxiv.org/abs/2212.03068 · HTML: https://mlsanity.com/paper/2212.03068/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [Socially Aware Motion Planning with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.08862/) (2017)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control](https://mlsanity.com/paper/2010.01856/) (2020)
- [Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning](https://mlsanity.com/paper/1910.11689/) (2019)
- [Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze](https://mlsanity.com/paper/1909.10400/) (2019)
- [DenseCAvoid: Real-time Navigation in Dense Crowds using Anticipatory Behaviors](https://mlsanity.com/paper/2002.03038/) (2020)
- [Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions](https://mlsanity.com/paper/2010.12239/) (2020)
- [Scalable Reinforcement Learning Policies for Multi-Agent Control](https://mlsanity.com/paper/2011.08055/) (2020)
- [Online Informative Path Planning for Active Classification Using UAVs](https://mlsanity.com/paper/1609.08446/) (2016)
- [Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learning](https://mlsanity.com/paper/1910.08811/) (2019)
- [Learning World Transition Model for Socially Aware Robot Navigation](https://mlsanity.com/paper/2011.03922/) (2020)
- [Optimal Trajectory Planning for Cinematography with Multiple Unmanned Aerial Vehicles](https://mlsanity.com/paper/2009.04234/) (2020)
- [Human-Centric Active Perception for Autonomous Observation](https://mlsanity.com/paper/2006.00037/) (2020)
- [Detection-Aware Trajectory Generation for a Drone Cinematographer](https://mlsanity.com/paper/2009.01565/) (2020)

## Built on by (most cited first, 1 of 1)

- [Decoupling Ego-Motion from Target Dynamics via Dual-Interval Motion Cues for UAV Detection](https://mlsanity.com/paper/2605.22605/) (2026)

## Abstract (arXiv)

In this paper, we consider the problem where a drone has to collect semantic information to classify multiple moving targets. In particular, we address the challenge of computing control inputs that move the drone to informative viewpoints, position and orientation, when the information is extracted using a "black-box" classifier, e.g., a deep learning neural network. These algorithms typically lack of analytical relationships between the viewpoints and their associated outputs, preventing their use in information-gathering schemes. To fill this gap, we propose a novel attention-based architecture, trained via Reinforcement Learning (RL), that outputs the next viewpoint for the drone favoring the acquisition of evidence from as many unclassified targets as possible while reasoning about their movement, orientation, and occlusions. Then, we use a low-level MPC controller to move the drone to the desired viewpoint taking into account its actual dynamics. We show that our approach not only outperforms a variety of baselines but also generalizes to scenarios unseen during training. Additionally, we show that the network scales to large numbers of targets and generalizes well to different movement dynamics of the targets.