# Towards Monocular Vision based Obstacle Avoidance through Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1706.09829 · HTML: https://mlsanity.com/paper/1706.09829/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2017.

## Built on by (most cited first, 23 of 23)

- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [Learning a State Representation and Navigation in Cluttered and Dynamic Environments](https://mlsanity.com/paper/2103.04351/) (2021)
- [NavRL: Learning Safe Flight in Dynamic Environments](https://mlsanity.com/paper/2409.15634/) (2024)
- [Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End](https://mlsanity.com/paper/2310.03581/) (2023)
- [A Safer Vision-based Autonomous Planning System for Quadrotor UAVs with Dynamic Obstacle Trajectory Prediction and Its Application with LLMs](https://mlsanity.com/paper/2311.12893/) (2023)
- [Vision-based Learning for Drones: A Survey](https://mlsanity.com/paper/2312.05019/) (2023)
- [A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance](https://mlsanity.com/paper/2103.06403/) (2021)
- [Goal-Guided Transformer-Enabled Reinforcement Learning for Efficient Autonomous Navigation](https://mlsanity.com/paper/2301.00362/) (2023)
- [Boundary-induced and scene-aggregated network for monocular depth prediction](https://mlsanity.com/paper/2102.13258/) (2021)
- [Boosting DNN Cold Inference on Edge Devices](https://mlsanity.com/paper/2206.07446/) (2022)
- [Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving](https://mlsanity.com/paper/1907.06838/) (2019)
- [A real-time dynamic obstacle tracking and mapping system for UAV navigation and collision avoidance with an RGB-D camera](https://mlsanity.com/paper/2209.08258/) (2022)
- [XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees](https://mlsanity.com/paper/2104.10818/) (2021)
- [Monocular Depth Distribution Alignment with Low Computation](https://mlsanity.com/paper/2203.04538/) (2022)
- [Smooth Trajectory Collision Avoidance through Deep Reinforcement Learning](https://mlsanity.com/paper/2210.06377/) (2022)
- [Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge](https://mlsanity.com/paper/2211.07130/) (2022)
- [Robot path planning using deep reinforcement learning](https://mlsanity.com/paper/2302.09120/) (2023)
- [NavRL++: A System-Level Framework for Improving Sim-to-Real Transfer in Reinforcement Learning-Based Robot Navigation](https://mlsanity.com/paper/2605.15559/) (2026)
- [Missing Velocity in Dynamic Obstacle Avoidance based on Deep Reinforcement Learning](https://mlsanity.com/paper/2112.12465/) (2021)
- [Energy-Efficient Parking Analytics System using Deep Reinforcement Learning](https://mlsanity.com/paper/2202.08973/) (2022)
- [Tactile Aware Dynamic Obstacle Avoidance in Crowded Environment with Deep Reinforcement Learning](https://mlsanity.com/paper/2406.13434/) (2024)
- [Monocular Obstacle Avoidance Based on Inverse PPO for Fixed-wing UAVs](https://mlsanity.com/paper/2411.18009/) (2024)
- [Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving](https://mlsanity.com/paper/2608.29772/) (2026)

## Abstract (arXiv)

Obstacle avoidance is a fundamental requirement for autonomous robots which operate in, and interact with, the real world. When perception is limited to monocular vision avoiding collision becomes significantly more challenging due to the lack of 3D information. Conventional path planners for obstacle avoidance require tuning a number of parameters and do not have the ability to directly benefit from large datasets and continuous use. In this paper, a dueling architecture based deep double-Q network (D3QN) is proposed for obstacle avoidance, using only monocular RGB vision. Based on the dueling and double-Q mechanisms, D3QN can efficiently learn how to avoid obstacles in a simulator even with very noisy depth information predicted from RGB image. Extensive experiments show that D3QN enables twofold acceleration on learning compared with a normal deep Q network and the models trained solely in virtual environments can be directly transferred to real robots, generalizing well to various new environments with previously unseen dynamic objects.