The accuracy of RGB-D SLAM systems is sensitive to the image quality, and can be significantly compromised in adverse situations such as when input images are blurry, lacking in texture features, or overexposed. In this paper, based on Continuous Direct Sparse Visual Odometry (CVO), we present a novel Keyframe-based CVO (KF-CVO) with intrinsic keyframe selection mechanism that effectively reduces the tracking error. We then extend KF-CVO to a RGB-D SLAM system, CVO SLAM, equipped with place recognition via ORB features, and joint bundle adjustment & pose graph optimization. Comprehensive evaluations on publicly available benchmarks show that the proposed RGB-D SLAM system achieves a higher success rate than current state-of-the-art-methods. The proposed system is more robust to difficult benchmark sequences than current state-of-the-art methods, where adverse situations such as rapid camera motions, environments lacking in texture, and overexposed images due to strong illumination exist.
4 January 2024 in IEEE Robotics and Automation Letters
Wepresent a novel motion planning framework for unmanned underwater vehicles (UUVs) - the first framework that applies Gaussian process motion planning to solve a 3D path planning problem for a 6-DoF robot in underwater environments. We address missions requiring UUVs to remain in close proximity to seafloor terrain, which must be achieved alongside collision avoidance. Our framework also considers the influence of current flows as part of the cost function, allowing for more accurate planning. To evaluate the performance of our proposed framework, we compare it with the widely used RRT* and STOMP algorithms over a range of underwater environments. Our experimental results demonstrate the stability and time efficiency of our framework.
16 December 2024 in IEEE Robotics and Automation Letters
With the growing demands for Autonomous Surface Vehicles (ASVs) in recent years, the number of ASVs being deployed for various maritime missions is expected to increase rapidly in the near future. However, it is still challenging for ASVs to perform sensor-based autonomous navigation in obstacle-filled and congested waterways, where perception errors, closely gathered vehicles and limited maneuvering space near buoys may cause difficulties in following the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). To address these issues, we propose a novel Distributional Reinforcement Learning based navigation system that can work with onboard LiDAR and odometry sensors to generate arbitrary thrust commands in continuous action space. Comprehensive evaluations of the proposed system in high-fidelity Gazebo simulations show its ability to decide whether to follow COLREGs or take other beneficial actions based on the scenarios encountered, offering superior performance in navigation safety and efficiency compared to systems using state-of-the-art Distributional RL, non-Distributional RL and classical methods.
Technology developments are demanding increasingly stringent requirements in terms of Electromagnetic Compatibility (EMC). For IC designers, this implies increasing Power Supply Rejection (PSR) while at the same time reducing the Icc spectrum. This work provides a theoretical analysis of the Peak Current Source with emitter degeneration (PCS-ED), a well known current mirror to achieve high PSR, which gets improved even further by the emitter resistance. The trade-off between the output current and the PSR were analyzed, as well as a sensitivity analysis to quantify the effects of the emitter degeneration. Experimental measurements have been performed to validate the immunity of an off-the-shelf bipolar transistor array from 100kHz up to 1GHz. Results showed that despite the small-signal analyses predicted a considerable improvement, the non-linear effects introduced by the input stage remained as the limiting factor in terms of PSR, leading to similar responses in the Peak Current Source (PCS) and the PCS-ED, despite one having much larger PSR than the other.