# AGPNet -- Autonomous Grading Policy Network

arXiv: https://arxiv.org/abs/2112.10877 · HTML: https://mlsanity.com/paper/2112.10877/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 20 Dec 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration](https://mlsanity.com/paper/2105.06411/) (2021)
- [YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers](https://mlsanity.com/paper/1811.05588/) (2018)
- [Learning hierarchical behavior and motion planning for autonomous driving](https://mlsanity.com/paper/2005.03863/) (2020)
- [Off-road Autonomous Vehicles Traversability Analysis and Trajectory Planning Based on Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/1909.06953/) (2019)
- [Robust Behavioral Cloning for Autonomous Vehicles using End-to-End Imitation Learning](https://mlsanity.com/paper/2010.04767/) (2020)
- [Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories](https://mlsanity.com/paper/1810.07225/) (2018)
- [A Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks](https://mlsanity.com/paper/1909.05214/) (2019)
- [Optimization-Based Framework for Excavation Trajectory Generation](https://mlsanity.com/paper/2010.14038/) (2020)
- [Developing a Simple Model for Sand-Tool Interaction and Autonomously Shaping Sand](https://mlsanity.com/paper/1908.02745/) (2019)
- [An Extension of BIM Using AI: a Multi Working-Machines Pathfinding Solution](https://mlsanity.com/paper/2105.06635/) (2021)

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

- [Towards Autonomous Grading In The Real World](https://mlsanity.com/paper/2206.06091/) (2022)

## Abstract (arXiv)

In this work, we establish heuristics and learning strategies for the autonomous control of a dozer grading an uneven area studded with sand piles. We formalize the problem as a Markov Decision Process, design a simulation which demonstrates agent-environment interactions and finally compare our simulator to a real dozer prototype. We use methods from reinforcement learning, behavior cloning and contrastive learning to train a hybrid policy. Our trained agent, AGPNet, reaches human-level performance and outperforms current state-of-the-art machine learning methods for the autonomous grading task. In addition, our agent is capable of generalizing from random scenarios to unseen real world problems.