13 December 2023 in IEEE Transactions on Automation Science and Engineering
It requires terrain classification for unmanned Mars Rover to identify the safe areas. The current deep learning-based semantic segmentation and object recognition suffer from a large number of parameters and long training time. In this paper, a lightweight segmentation framework called Mobile-DeepRFB is proposed for the Martian terrain classification. It improves from the DeepLabV3 $+$ by taking the MobileNetV3 as the backbone module to decrease the parameters and the Receptive Field Block (RFB) module to strengthen the feature extraction capability as well as to enlarge the receptive field. Experimental results on the NASA Mars terrain dataset AI4MARS show that the presented method reduces 94% about the parameter number and improves the mean pixel accuracy by 2% compared to the existing ResNet101 and Xception backbone networks. The deployment of this framework on a low-computing power embedded platform (NVIDIA Jetson Xavier) demonstrates its great potential to apply to Mars rovers. Note to Practitioners —This paper was motivated by the problem of terrain classification of planetary rovers. Existing methods are typically based on semantic segmentation technology to recognize various terrains while suffering from the drawback of a large number of parameters. We propose a lightweight segmentation framework to address this issue. In particular, the lightweight backbone network is applied to significantly reduce the number of parameters. The receptive field module is substantially improved to enhance the feature extraction capability. Eventually, we deploy the framework on a low-computing platform. Experimental tests show that the framework can significantly reduce the number of network parameters and it can be used for planetary rovers with limited computational resources.
11 September 2023 in IEEE Transactions on Intelligent Transportation Systems
The multi-dimensional force/torque decoupling and calibration is extremely crucial to increase the accuracy of the Wheel Force Transducer/Sensor (WFT). A novel interpretable nonlinear decoupling and calibration approach to WFT is presented. A physical interpretable prime-error framework is developed such that the linear prime part accounts for most force-voltage responses while the nonlinear error part accounts for the gross error deviation. The conventional least-square decoupling is improved with the delicate nonlinear error modeling using a polynomial base module and a hyperbolic activation function. The developed framework is proved to be mathematically solvable and physically feasible by a two-step calibration scheme. A two-axis WFT is tested and compared with the proposed interpretable nonlinear decoupling model (IND), the least-square-based method (LSM), and the error-based neural network model (eNN). Results demonstrate that the proposed IND provides an accurate, practical, and effective scheme for modeling and calibrating WFTs and maintains a good balance among accuracy, generalization ability, and computational efficiency for real applications.
18 March 2024 in IEEE Transactions on Automation Science and Engineering
It needs to predict the soft terrain trafficability of the Mars rover to avoid hazards in emergencies. The current prediction models of Mars terrain trafficability simply transfer information between humans and machines, with lower levels of human-machine interaction fusion, which hinders the creation of effective emergency handling measures. In this paper, a human-in-the-loop multi-indices fusion decision framework called HITL-FD is proposed for Mars rover trafficability prediction. The framework deals with the fuzziness of the trafficability boundaries by fuzzy theory, achieving the fusion processing of multiple evaluation indices and adopting a fuzzy decision tree algorithm to predict trafficability. Additionally, human-assisted decision is incorporated into the decision loop, and a reward function based on decision error is proposed to generate a closed-loop decision framework. The experimental results show that the framework has excellent trafficability prediction performance and reduces 5.1% of MAYBE terrain uncertainty compared to machine-based decision. Note to Practitioners —The trafficability prediction is crucial for Mars rovers traversing soft terrain to avoid emergencies including sinkage. Conventional trafficability prediction models have a low degree of human-machine fusion, which is not beneficial for applications of planetary rovers in practical engineering. In this paper, a multi-indices human-machine fusion decision framework is proposed, specifically designed for predicting the trafficability of Mars rover. In this framework, fuzzy theory is used to address the ambiguity associated with trafficability boundaries. It provides an overall evaluation of trafficability by fusing a single index and the use of a fuzzy decision tree algorithm to make predictions regarding trafficability. Furthermore, the framework incorporates human-assisted decision-making within the closed decision loop, and proposes a reward function based on decision error. Experimental results show that the framework can increase the correctness of trafficability prediction.