This paper presents the design, modeling, and experimental validation of CapsuleBot, a compact hybrid aerial-ground vehicle designed for long-term covert reconnaissance. CapsuleBot combines the manoeuvrability of bicopter in the air with the energy efficiency and noise reduction of ground vehicles on the ground. To accomplish this, a structure named actuated-wheel-rotor has been designed, utilizing a sole motor for both the unilateral rotor tilting in the bicopter configuration and the wheel movement in ground mode. CapsuleBot comes equipped with two of these structures, enabling it to attain hybrid aerial-ground propulsion with just four motors. Importantly, the decoupling of motion modes is achieved without the need for additional drivers, enhancing the versatility and robustness of the system. Furthermore, we have designed the full dynamics and control for aerial and ground locomotion based on the bicopter model and the two-wheeled self-balancing vehicle model. The performance of CapsuleBot has been validated through experiments. The results demonstrate that CapsuleBot produces 40.53% less noise in ground mode and consumes 99.35% less energy, highlighting its potential for long-term covert reconnaissance applications.
The intention of the target can help us to estimate its future motion state more accurately. This paper proposes an intention-aware planner to enhance safety and robustness in aerial tracking applications. Firstly, we utilize the Mediapipe framework to estimate target's pose. A risk assessment function and a state observation function are designed to predict the target intention. Afterwards, an intention-driven hybrid A* method is proposed for target motion prediction, ensuring that the target's future positions align with its intention. Finally, an intention-aware optimization approach, in conjunction with particular penalty formulations, is designed to generate a spatial-temporal optimal trajectory. Benchmark comparisons validate the superior performance of our proposed methodology across diverse scenarios. This is attributed to the integration of the target intention into the planner through coupled formulations.
Roller-Quadrotor is a novel hybrid terrestrial and aerial quadrotor that combines the elevated maneuverability of the quadrotor with the lengthy endurance of the ground vehicle. This work presents the design, modeling, and experimental validation of Roller-Quadrotor. Flying is achieved through a quadrotor configuration, and four actuators providing thrust. Rolling is supported by unicycle-driven and rotor-assisted turning structure. During terrestrial locomotion, the vehicle needs to overcome rolling and turning resistance, thus saving energy compared to flight mode. This work overcomes the challenging problems of general rotorcraft, reduces energy consumption and allows to through special terrain, such as narrow gaps. It also solves the obstacle avoidance challenge faced by terrestrial robots by flying. We design the models and controllers for the vehicle. The experiment results show that it can switch between aerial and terrestrial locomotion, and be able to safely pass through a narrow gap half the size of its diameter. Besides, it is capable of rolling a distance approximately 3.8 times as much as flying or operating about 42.2 times as lengthy as flying. These results demonstrate the feasibility and effectiveness of the structure and control in rolling through special terrain and energy saving.
Catching high-speed targets in the flight is a complex and typical highly dynamic task. In this paper, we propose Catch Planner, a planning-with-decision scheme for catching. For sequential decision making, we propose a policy search method based on deep reinforcement learning. In order to make catching adaptive and flexible, we propose a trajectory optimization method to jointly optimize the highly coupled catching time and terminal state while considering the dynamic feasibility and safety. We also propose a flexible constraint transcription method to catch targets at any reasonable attitude and terminal position bias. The proposed Catch Planner provides a new paradigm for the combination of learning and planning and is integrated on the quadrotor designed by ourselves, which runs at 100$hz$ on the onboard computer. Extensive experiments are carried out in real and simulated scenes to verify the robustness of the proposed method and its expansibility when facing a variety of high-speed flying targets.
State estimation is important for a variety of tasks, from forecasting to substituting for unmeasured states in feedback controllers. Performing real-time state estimation for PDEs using provably and rapidly converging observers, such as those based on PDE backstepping, is computationally expensive and in many cases prohibitive. We propose a framework for accelerating PDE observer computations using learning-based approaches that are much faster while maintaining accuracy. In particular, we employ the recently-developed Fourier Neural Operator (FNO) to learn the functional mapping from the initial observer state and boundary measurements to the state estimate. By employing backstepping observer gains for previously-designed observers with particular convergence rate guarantees, we provide numerical experiments that evaluate the increased computational efficiency gained with FNO. We consider the state estimation for three benchmark PDE examples motivated by applications: first, for a reaction-diffusion (parabolic) PDE whose state is estimated with an exponential rate of convergence; second, for a parabolic PDE with exact prescribed-time estimation; and, third, for a pair of coupled first-order hyperbolic PDEs that modeling traffic flow density and velocity. The ML-accelerated observers trained on simulation data sets for these PDEs achieves up to three orders of magnitude improvement in computational speed compared to classical methods. This demonstrates the attractiveness of the ML-accelerated observers for real-time state estimation and control.
With the ability of providing direct and accurate enough range measurements, light detection and ranging (LiDAR) is playing an essential role in localization and detection for autonomous vehicles. Since single LiDAR suffers from hardware failure and performance degradation intermittently, we present a multi-LiDAR integration scheme in this article. Our framework tightly couples multiple non-repetitive scanning LiDARs with inertial, encoder, and global navigation satellite system (GNSS) into pose estimation and simultaneous global map generation. Primarily, we formulate a precise synchronization strategy to integrate isolated sensors, and the extracted feature points from separate LiDARs are merged into a single sweep. The fused scans are introduced to compute the scan-matching correspondences, which can be further refined by additional real-time kinematic (RTK) measurements. Based thereupon, we construct a factor graph along with the inertial preintegration result, estimated ground constraints, and RTK data. For the purpose of maintaining a restricted number of poses for estimation, we deploy a keyframe based sliding-window optimization strategy in our system. The real-time performance is guaranteed with multi-threaded computation, and extensive experiments are conducted in challenging scenarios. Experimental results show that the utilization of multiple LiDARs boosts the system performance in both robustness and accuracy.
Underwater robots in shallow waters usually suffer from strong wave forces, which may frequently exceed robot's control constraints. Learning-based controllers are suitable for disturbance rejection control, but the excessive disturbances heavily affect the state transition in Markov Decision Process (MDP) or Partially Observable Markov Decision Process (POMDP). Also, pure learning procedures on targeted system may encounter damaging exploratory actions or unpredictable system variations, and training exclusively on a prior model usually cannot address model mismatch from the targeted system. In this paper, we propose a transfer learning framework that adapts a control policy for excessive disturbance rejection of an underwater robot under dynamics model mismatch. A modular network of learning policies is applied, composed of a Generalized Control Policy (GCP) and an Online Disturbance Identification Model (ODI). GCP is first trained over a wide array of disturbance waveforms. ODI then learns to use past states and actions of the system to predict the disturbance waveforms which are provided as input to GCP (along with the system state). A transfer reinforcement learning algorithm using Transition Mismatch Compensation (TMC) is developed based on the modular architecture, that learns an additional compensatory policy through minimizing mismatch of transitions predicted by the two dynamics models of the source and target tasks. We demonstrated on a pose regulation task in simulation that TMC is able to successfully reject the disturbances and stabilize the robot under an empirical model of the robot system, meanwhile improve sample efficiency.