Causal Correction and Compensation Network for Robotics: Applications and Validation in Continuous Control
Open Access
- 1 September 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (17) , 9628
Abstract
Deep Reinforcement Learning (DRL) has achieved remarkable success in robotic control, autonomous driving, and game-playing agents. However, its decision-making process often remains a black box, lacking both interpretability and verifiability. In robotic control tasks, developers cannot pinpoint decision errors or precisely adjust control strategies based solely on observed robot behaviors. To address this challenge, this work proposes an interpretable DRL framework based on a Causal Correction and Compensation Network (C2-Net), which systematically captures the causal relationships underlying decision-making and enhances policy robustness. C2-Net integrates a Graph Neural Network-based Neural Causal Model (GNN-NCM) to compute causal influence weights for each action. These weights are then dynamically applied to correct and compensate the raw policy outputs, thereby balancing performance optimization and transparency. This work validates the approach on OpenAI Gym’s Hopper, Walker2d, and Humanoid environments, as well as the multi-agent AzureLoong platform built on Isaac Gym. In terms of convergence speed, final return, and policy robustness, experimental results show that C2-Net achieves higher performance over both non-causal baselines and conventional attention-based models. Moreover, it provides rich causal explanations for its decisions. The framework represents a principled shift from correlation to causation and offers a practical solution for the safe and reliable deployment of multi-robot systems.Keywords
Funding Information
- National Natural Science Foundation of China (62103009, 4202005)
- Natural Science Foundation of Beijing Municipality (62103009, 4202005)
This publication has 23 references indexed in Scilit:
- Survey on Graph Neural NetworksIEEE Access, 2024
- Causal deconfounding deep reinforcement learning for mobile robot motion planningKnowledge-Based Systems, 2024
- Computer Vision – ECCV 20242024
- A causal-based approach to explain, predict and prevent failures in robotic tasksRobotics and Autonomous Systems, 2023
- Why Did I Fail? A Causal-Based Method to Find Explanations for Robot FailuresIEEE Robotics and Automation Letters, 2022
- Causal Feature Selection With Dual CorrectionIEEE Transactions on Neural Networks and Learning Systems, 2022
- Graph Convolutional Neural Network for Human Action Recognition: A Comprehensive SurveyIEEE Transactions on Artificial Intelligence, 2021
- The rational use of causal inference to guide reinforcement learning strengthens with agenpj Science of Learning, 2020
- Free-Lunch Saliency via Attention in Atari Agents2019
- CAUSALITY: MODELS, REASONING, AND INFERENCE, by Judea Pearl, Cambridge University Press, 2000Econometric Theory, 2003