Fengyu Quan

Dongyu Yan, Jianheng Liu, Fengyu Quan et al.

Actively planning sensor views during object reconstruction is crucial for autonomous mobile robots. An effective method should be able to strike a balance between accuracy and efficiency. In this paper, we propose a seamless integration of the emerging implicit representation with the active reconstruction task. We build an implicit occupancy field as our geometry proxy. While training, the prior object bounding box is utilized as auxiliary information to generate clean and detailed reconstructions. To evaluate view uncertainty, we employ a sampling-based approach that directly extracts entropy from the reconstructed occupancy probability field as our measure of view information gain. This eliminates the need for additional uncertainty maps or learning. Unlike previous methods that compare view uncertainty within a finite set of candidates, we aim to find the next-best-view (NBV) on a continuous manifold. Leveraging the differentiability of the implicit representation, the NBV can be optimized directly by maximizing the view uncertainty using gradient descent. It significantly enhances the method's adaptability to different scenarios. Simulation and real-world experiments demonstrate that our approach effectively improves reconstruction accuracy and efficiency of view planning in active reconstruction tasks. The proposed system will open source at https://github.com/HITSZ-NRSL/ActiveImplicitRecon.git.

Yueqian Liu, Fengyu Quan, Haoyao Chen

Omnidirectional micro aerial vehicles (OMAVs) are more capable of doing environmentally interactive tasks due to their ability to exert full wrenches while maintaining stable poses. However, OMAVs often incorporate additional actuators and complex mechanical structures to achieve omnidirectionality. Obtaining precise mathematical models is difficult, and the mismatch between the model and the real physical system is not trivial. The large model-plant mismatch significantly degrades overall system performance if a non-adaptive model predictive controller (MPC) is used. This work presents the $\mathcal{L}_1$-MPC, an adaptive nonlinear model predictive controller for accurate 6-DOF trajectory tracking of an overactuated tiltrotor hexacopter in the presence of model uncertainties and external disturbances. The $\mathcal{L}_1$-MPC adopts a cascaded system architecture in which a nominal MPC is followed and augmented by an $\mathcal{L}_1$ adaptive controller. The proposed method is evaluated against the non-adaptive MPC, the EKF-MPC, and the PID method in both numerical and PX4 software-in-the-loop simulation with Gazebo. The $\mathcal{L}_1$-MPC reduces the tracking error by around 90% when compared to a non-adaptive MPC, and the $\mathcal{L}_1$-MPC has lower tracking errors, higher uncertainty estimation rates, and less tuning requirements over the EKF-MPC. We will make the implementations, including the hardware-verified PX4 firmware and Gazebo plugins, open-source at https://github.com/HITSZ-NRSL/omniHex.

Dongyu Yan, Guanyu Huang, Fengyu Quan et al.

Panoramic observation using fisheye cameras is significant in virtual reality (VR) and robot perception. However, panoramic images synthesized by traditional methods lack depth information and can only provide three degrees-of-freedom (3DoF) rotation rendering in VR applications. To fully preserve and exploit the parallax information within the original fisheye cameras, we introduce MSI-NeRF, which combines deep learning omnidirectional depth estimation and novel view synthesis. We construct a multi-sphere image as a cost volume through feature extraction and warping of the input images. We further build an implicit radiance field using spatial points and interpolated 3D feature vectors as input, which can simultaneously realize omnidirectional depth estimation and 6DoF view synthesis. Leveraging the knowledge from depth estimation task, our method can learn scene appearance by source view supervision only. It does not require novel target views and can be trained conveniently on existing panorama depth estimation datasets. Our network has the generalization ability to reconstruct unknown scenes efficiently using only four images. Experimental results show that our method outperforms existing methods in both depth estimation and novel view synthesis tasks.

Fengyu Quan, Huisheng Huang, Hongjie Zeng et al.

The aerial manipulator (AM) is a systematic operational robotic platform in high standard on algorithm robustness. Directly deploying the algorithms to the practical system will take numerous trial and error costs and even cause destructive results. In this paper, a new modular simulation platform is designed to evaluate aerial manipulation related algorithms before deploying. In addition, to realize a fully autonomous aerial grasping, a series of algorithm modules consisting a complete workflow are designed and integrated in the simulation platform, including perception, planning and control modules. This framework empowers the AM to autonomously grasp remote targets without colliding with surrounding obstacles relying only on on-board sensors. Benefiting from its modular design, this software architecture can be easily extended with additional algorithms. Finally, several simulations are performed to verify the effectiveness of the proposed system.