28 June 2024 in IEEE Transactions on Instrumentation and Measurement
Simultaneous Localization and Mapping (SLAM) is crucial for the progression of autonomous systems, including autonomous driving, Augmented Reality (AR), and robotics. Traditionally reliant on static environments, SLAM now confronts the complexities of the dynamic real world. Advancements in Artificial Intelligence (AI) and deep learning are propelling SLAM towards enhanced management of these dynamics. This survey presents a comprehensive analysis of visual SLAM in dynamic settings, an area significantly advanced by semantic understanding and sensor fusion technologies. It begins with an examination of geometric SLAM methods, addressing their efficacy in static contexts and limitations amidst dynamic changes. Subsequently, it focuses on semantic-based SLAM techniques, emphasizing their capacity for nuanced environmental representation and dynamic object management. Additionally, the survey explores cutting-edge multi-sensor fusion strategies that substantially improve SLAM’s robustness and precision in intricate environments. We offer a critical review of persistent challenges, including computational demands, sensor calibration, and the imperative for real-time processing. The survey concludes by identifying fertile areas for future research, highlighting the ongoing potential for SLAM technology innovation to adapt to the ever-changing environmental dynamics.
7 August 2024 in IEEE Robotics and Automation Letters
This letter proposes a novel bionic bird claw with a digit-locking mechanism inspired by a tendon-locking mechanism (TLM). First, the biological mechanisms of both the bird digit-locked TLM (tendon locking) and the leg automatic digit flexion mechanism (ADFM) (quick digit flexion) of birds are introduced. Then, a digit-locking mechanism that locks the flexion tendon on the digit based on the TLM is proposed, requiring only a tensioned cable to unlock the digit. A parallelogram fold leg mechanism is designed based on the ADFM to drive the digit's flexion and locking motions. The digit locking and unlocking statics, the claw's gripping range, and the gripping force were analyzed. Finally, a prototype is developed, and several experiments are conducted to measure digit locking and unlocking force, digit loading, claw gripping range, claw loading capability, and multi-angle dive grabbing of the claw. The load-to-weight ratio of the claw is 45.0–87.6. Moreover, the success rate of claw-grasping branches is found to reach 95 ${\%}$ . The bionic bird claw closely mimics the TLM of the bird claw and demonstrates high reliability, serving as a valuable reference for unmanned aerial vehicles in perching, grabbing, and carrying tasks.
2 May 2020 in Frontiers of Mechanical Engineering
This study presents two kinds of rolling robots that are able to roll by deforming their outer shapes with a single degree of freedom. Each robot is an essential multi-loop planar expandable linkage constructed by a concave outer loop and several inner parallelogram loops. In this study, the mechanical design of the robots is introduced. Dynamic rolling process is further analyzed on the basis of zero moment point method, and a morphing strategy is proposed to guarantee a stable dynamic rolling process. A novel passive rolling locomotion is also developed, which enables the robots to roll and stand on a slope. To verify the design, two prototypes are manufactured, wherein the dynamic and passive rolling locomotion are carried out.
2 December 2024 in IEEE Transactions on Instrumentation and Measurement
Traditional visual SLAM methods excel in static, texture-rich environments, but may struggle in dynamic, textureless environments. Recent advances in dynamic SLAM incorporate deep learning techniques to eliminate dynamic objects. However, these methods may suffer from unrecognizable dynamic objects, and removing dynamic feature points exacerbates feature scarcity. To address the limitations, we propose MSSD-SLAM, a multi-feature semantic RGB-D Inertial SLAM system that incorporates point, line, and plane features to enhance robustness and enrich static map fidelity. By embedding structural constraints on 3D spatial features constructed from multi-frame observations, it guarantees geometric consistency and accurate camera pose estimation, supporting subsequent dynamic object detection. A novel Dynamic Filter has been developed that efficiently handles both semantically recognizable and unrecognizable objects by amalgamating semantic segmentation, structural constraints, and IMU measurements. Short-term dynamic objects are detected by the consistency of multi-source information, while long-term dynamic objects, which may remain static temporarily, are identified through covisible projection among multiple frames. Validation on the TUM dataset and real-world scenarios demonstrates that the localization accuracy of MSSD-SLAM outperforms ORB-SLAM3 and Dynamic-VINS by 76% and 64%, respectively, indicating that our algorithm exhibits superior accuracy and robustness in dynamic indoor scenes compared to state-of-the-art algorithms.
31 August 2026 in Journal of Bionic Engineering