Machine Learning Approaches for Sensor Fusion in Robotic Perception
Abstract
Sensor fusion is a crucial aspect of enhancing the perception capabilities of robots, enabling them to operate effectively in dynamic and complex environments. This paper explores various machine learning approaches for sensor fusion in robotic perception. We discuss the utilization of deep learning models, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), to integrate data from diverse sensors, including cameras, LiDAR, and inertial sensors. Through a comprehensive review of the literature, we analyze the strengths and limitations of these techniques, highlighting the potential for improved accuracy and robustness in robot perception. Moreover, we discuss the importance of real-time processing and resource-efficient algorithms for practical deployment. In conclusion, this paper provides valuable insights into the state of the art in sensor fusion for robotic perception and points out future research directions in this domain.
References
Chaitanya Krishna Suryadevara, “TOWARDS PERSONALIZED HEALTHCARE - AN INTELLIGENT MEDICATION RECOMMENDATION SYSTEM”, IEJRD - International Multidisciplinary Journal, vol. 5, no. 9, p. 16, Dec. 2020.
Suryadevara, Chaitanya Krishna, Predictive Modeling for Student Performance: Harnessing Machine Learning to Forecast Academic Marks (December 22, 2018). International Journal of Research in Engineering and Applied Sciences (IJREAS), Vol. 8 Issue 12, December-2018, Available at SSRN: https://ssrn.com/abstract=4591990
Suryadevara, Chaitanya Krishna, Unveiling Urban Mobility Patterns: A Comprehensive Analysis of Uber (December 21, 2019). International Journal of Engineering, Science and Mathematics, Vol. 8 Issue 12, December 2019, Available at SSRN: https://ssrn.com/abstract=4591998
Chaitanya Krishna Suryadevara. (2019). A NEW WAY OF PREDICTING THE LOAN APPROVAL PROCESS USING ML TECHNIQUES. International Journal of Innovations in Engineering Research and Technology, 6(12), 38–48. Retrieved from https://repo.ijiert.org/index.php/ijiert/article/view/3654
Chaitanya Krishna Suryadevara. (2020). GENERATING FREE IMAGES WITH OPENAI’S GENERATIVE MODELS. International Journal of Innovations in Engineering Research and Technology, 7(3), 49–56. Retrieved from https://repo.ijiert.org/index.php/ijiert/article/view/3653
Chaitanya Krishna Suryadevara. (2020). REAL-TIME FACE MASK DETECTION WITH COMPUTER VISION AND DEEP LEARNING: English. International Journal of Innovations in Engineering Research and Technology, 7(12), 254–259. Retrieved from https://repo.ijiert.org/index.php/ijiert/article/view/3184
Chaitanya Krishna Suryadevara. (2021). ENHANCING SAFETY: FACE MASK DETECTION USING COMPUTER VISION AND DEEP LEARNING. International Journal of Innovations in Engineering Research and Technology, 8(08), 224–229. Retrieved from https://repo.ijiert.org/index.php/ijiert/article/view/3672
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259.
Zhang, Z. (2016). A review of 3D object detection methods. The International Journal of Robotics Research, 36(8), 801-824.
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Reiman, C., & Makris, D. (2007). Multi-sensor fusion for object tracking with adaptive confidence functions. Image and Vision Computing, 25(9), 1469-1481.
Li, B., Zhang, Z., & Liu, Z. (2016). A multi-sensor fusion method for real-time 3D object tracking. IEEE Transactions on Industrial Informatics, 12(2), 551-560.