Multi-sensor Fusion Incorporating Adaptive Transformation for Reconfigurable Pavement Sweeping Robot

Povendhan, A.P.; Yi, Lim; Hayat, Abdullah Aamir; Le, Anh Vu; Kaspar, Kai; Ramalingam, Balakrishnan; Elara, Mohan Rajesh

doi:10.1109/iros51168.2021.9636464

Cited by 9 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, reconfigurable robotic systems present innovative approaches to robot design and functionality. The limitations of fixed-morphology cleaning and maintenance robots can be addressed by introducing a heuristic framework for reconfigurable robotic system design such as the one in [50], while the use of sensors integrated for navigation has been highlighted in [51,52]. A taxonomy and evaluation framework for self-reconfigurable robots based on mechanism reconfigurability and autonomy levels was presented in [53], along with an evaluation of a staircase-climbing robot.…”

Section: Methods Advantages Limitationsmentioning

confidence: 99%

Deep Learning Based Fall Recognition and Forecasting for Reconfigurable Stair-Accessing Service Robots

Ong,

Hayat,

Gomez

et al. 2024

Mathematics

View full text Add to dashboard Cite

This paper presents a comprehensive study on fall recognition and forecasting for reconfigurable stair-accessing robots by leveraging deep learning techniques. The proposed framework integrates machine learning algorithms and recurrent neural networks (RNNs), specifically Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM), for fall detection of service robots on staircases. The reconfigurable stair-accessing robot sTetro serves as the platform, and the fall data required for training models are generated in a simulation environment. The two machine learning algorithms are compared and their effectiveness on the fall recognition task is reported. The results indicate that the BiLSTM model effectively classifies falls with a median categorical accuracy of 94.10% in simulation and 90.02% with limited experiments. Additionally, the BiLSTM model can be used for forecasting, which is practically valuable for making decisions well before the onset of a free fall. This study contributes insights into the design and implementation of fall detection systems for service robots used to navigate staircases through deep learning approaches. Our experimental and simulation data, along with the simulation steps, are available for reference and analysis via the shared link.

show abstract