--The high mobility of unmanned aerial vehicles (UA Vs) enables them to be used in various civilian fields, such as rescue and cargo transport. Path-following is a crucial way to perform these tasks while sensing and collision avoidance are essential for safe flight. In this paper, we investigate how to efficiently and accurately achieve path-following, obstacle sensing and avoidance subtasks, as well as their conflict-free fusion scheduling. Firstly, a high precision deep reinforcement learning (DRL)-based UA V formation path-following model is developed, and the reward function with adaptive weights is designed from the perspective of distance and velocity errors. Then, we use integrated sensing and communication (ISAC) signals to detect the obstacle and derive the Cram er-Rao lower bound (CRLB) for obstacle sensing by information-level fusion, based on which we propose the variable formation enhanced obstacle position estimation (VFEO) algorithm. In addition, an online obstacle avoidance scheme without pretraining is designed to solve the sparse reward. Finally, with the aid of null space based (NSB) behavioral method, we present a hierarchical subtasks fusion strategy. Simulation results demonstrate the effectiveness and superiority of the subtask algorithms and the hierarchical fusion strategy. Index T erms --UA V formation, path-following, cooperative sensing, obstacle avoidance, hierarchical subtasks fusion, integrated sensing and communication. ITH the development of wireless communication and intelligent control, unmanned aerial vehicle (UA V) plays an important role in the civilian field. However, the detection and communication capabilities of a single UA V are limited. Multiple UA Vs provide enhanced coverage and stability [1], enabling them to perform various tasks such as rescue, cargo transport, emergency communications, and area search [2].

We present a geometric neural network-based tracking controller for systems evolving on matrix Lie groups under unknown dynamics, actuator faults, and bounded disturbances. Leveraging the left-invariance of the tangent bundle of matrix Lie groups, viewed as an embedded submanifold of the vector space $\R^{N\times N}$, we propose a set of learning rules for neural network weights that are intrinsically compatible with the Lie group structure and do not require explicit parameterization. Exploiting the geometric properties of Lie groups, this approach circumvents parameterization singularities and enables a global search for optimal weights. The ultimate boundedness of all error signals -- including the neural network weights, the coordinate-free configuration error function, and the tracking velocity error -- is established using Lyapunov's direct method. To validate the effectiveness of the proposed method, we provide illustrative simulation results for decentralized formation control of multi-agent systems on the Special Euclidean group.

We improve the accuracy of Guidance & Control Networks (G&CNETs), trained to represent the optimal control policies of a time-optimal transfer and a mass-optimal landing, respectively. In both cases we leverage the dynamics of the spacecraft, described by Ordinary Differential Equations which incorporate a neural network on their right-hand side (Neural ODEs). Since the neural dynamics is differentiable, the ODEs sensitivities to the network parameters can be computed using the variational equations, thereby allowing to update the G&CNET parameters based on the observed dynamics. We start with a straightforward regression task, training the G&CNETs on datasets of optimal trajectories using behavioural cloning. These networks are then refined using the Neural ODE sensitivities by minimizing the error between the final states and the target states. We demonstrate that for the orbital transfer, the final error to the target can be reduced by 99% on a single trajectory and by 70% on a batch of 500 trajectories. For the landing problem the reduction in error is around 98-99% (position) and 40-44% (velocity). This step significantly enhances the accuracy of G&CNETs, which instills greater confidence in their reliability for operational use. We also compare our results to the popular Dataset Aggregation method (DaGGER) and allude to the strengths and weaknesses of both methods.

In this paper, a comparison analysis between geometric impedance controls (GICs) derived from two different potential functions on SE(3) for robotic manipulators is presented. The first potential function is defined on the Lie group, utilizing the Frobenius norm of the configuration error matrix. The second potential function is defined utilizing the Lie algebra, i.e., log-map of the configuration error. Using a differential geometric approach, the detailed derivation of the distance metric and potential function on SE(3) is introduced. The GIC laws are respectively derived from the two potential functions, followed by extensive comparison analyses. In the qualitative analysis, the properties of the error function and control laws are analyzed, while the performances of the controllers are quantitatively compared using numerical simulation.

Micron-scale robots ($\mu$bots) have recently shown great promise for emerging medical applications. Accurate controlling $\mu$bots, while critical to their successful deployment, is challenging. In this work, we consider the problem of tracking a reference trajectory using a $\mu$bot in the presence of disturbances and uncertainty. The disturbances primarily come from Brownian motion and other environmental phenomena, while the uncertainty originates from errors in the model parameters. We model the $\mu$bot as an uncertain unicycle that is controlled by a global magnetic field. To compensate for disturbances and uncertainties, we develop a nonlinear mismatch controller. We define the model mismatch error as the difference between our model's predicted velocity and the actual velocity of the $\mu$bot. We employ a Gaussian Process to learn the model mismatch error as a function of the applied control input. Then we use a least-squares minimization to select a control action that minimizes the difference between the actual velocity of the $\mu$bot and a reference velocity. We demonstrate the online performance of our joint learning and control algorithm in simulation, where our approach accurately learns the model mismatch and improves tracking performance. We also validate our approach in an experiment and show that certain error metrics are reduced by up to $40\%$.

When legged robots impact their environment, they undergo large changes in their velocities in a short amount of time. Measuring and applying feedback to these velocities is challenging, further complicated by uncertainty in the impact model and impact timing. This work proposes a general framework for adapting feedback control during impact by projecting the control objectives to a subspace that is invariant to the impact event. The resultant controller is robust to uncertainties in the impact event while maintaining maximum control authority over the impact-invariant subspace. We demonstrate the improved performance of the projection over other commonly used heuristics on a walking controller for a planar five-link-biped. The projection is also applied to jumping, box jumping on to a platform 0.4 m tall, and running controllers for the compliant 3D bipedal robot, Cassie. The modification is easily applied to these various controllers and is a critical component to deploying on the physical robot.

This study presents incremental correction methods for refining neural network parameters or control functions entering into a continuous-time dynamic system to achieve improved solution accuracy in satisfying the interim point constraints placed on the performance output variables. The proposed approach is to linearise the dynamics around the baseline values of its arguments, and then to solve for the corrective input required to transfer the perturbed trajectory to precisely known or desired values at specific time points, i.e., the interim points. Depending on the type of decision variables to adjust, parameter correction and control function correction methods are developed. These incremental correction methods can be utilised as a means to compensate for the prediction errors of pre-trained neural networks in real-time applications where high accuracy of the prediction of dynamical systems at prescribed time points is imperative. In this regard, the online update approach can be useful for enhancing overall targeting accuracy of finite-horizon control subject to point constraints using a neural policy. Numerical example demonstrates the effectiveness of the proposed approach in an application to a powered descent problem at Mars.

Autonomous underwater vehicles (AUV) are commonly used in many underwater applications. Recently, the usage of multi-rotor unmanned autonomous vehicles (UAV) for marine applications is receiving more attention in the literature. Usually, both platforms employ an inertial navigation system (INS), and aiding sensors for an accurate navigation solution. In AUV navigation, Doppler velocity log (DVL) is mainly used to aid the INS, while for UAVs, it is common to use global navigation satellite systems (GNSS) receivers. The fusion between the aiding sensor and the INS requires a definition of step size parameter in the estimation process. It is responsible for the solution frequency update and, eventually, its accuracy. The choice of the step size poses a tradeoff between computational load and navigation performance. Generally, the aiding sensors update frequency is considered much slower compared to the INS operating frequency (hundreds Hertz). Such high rate is unnecessary for most platforms, specifically for low dynamics AUVs. In this work, a supervised machine learning based adaptive tuning scheme to select the proper INS step size is proposed. To that end, a velocity error bound is defined, allowing the INS/DVL or the INS/GNSS to act in a sub-optimal working conditions, and yet minimize the computational load. Results from simulations and field experiment show the benefits of using the proposed approach. In addition, the proposed framework can be applied to any other fusion scenarios between any type of sensors or platforms.

Deep deterministic policy gradient (DDPG) based car-following strategy can break through the constraints of the differential equation model due to the ability of exploration on complex environments. However, the car-following performance of DDPG is usually degraded by unreasonable reward function design, insufficient training and low sampling efficiency. In order to solve this kind of problem, a hybrid car-following strategy based on DDPG and cooperative adaptive cruise control (CACC) is proposed. Firstly, the car-following process is modeled as markov decision process to calculate CACC and DDPG simultaneously at each frame. Given a current state, two actions are obtained from CACC and DDPG, respectively. Then an optimal action, corresponding to the one offering a larger reward, is chosen as the output of the hybrid strategy. Meanwhile, a rule is designed to ensure that the change rate of acceleration is smaller than the desired value. Therefore, the proposed strategy not only guarantees the basic performance of car-following through CACC, but also makes full use of the advantages of exploration on complex environments via DDPG. Finally, simulation results show that the car-following performance of proposed strategy is improved significantly as compared with that of DDPG and CACC in the whole state space.