Autonomous Robots最新文献

This work introduces a novel detector, bounded false-alarm rate (BFAR), for distinguishing true detections from noise in radar data, leading to improved accuracy in radar odometry estimation. Scanning frequency-modulated continuous wave (FMCW) radars can serve as valuable tools for localization and mapping under low visibility conditions. However, they tend to yield a higher level of noise in comparison to the more commonly employed lidars, thereby introducing additional challenges to the detection process. We propose a new radar target detector called BFAR which uses an affine transformation of the estimated noise level compared to the classical constant false-alarm rate (CFAR) detector. This transformation employs learned parameters that minimize the error in odometry estimation. Conceptually, BFAR can be viewed as an optimized blend of CFAR and fixed-level thresholding designed to minimize odometry estimation error. The strength of this approach lies in its simplicity. Only a single parameter needs to be learned from a training dataset when the affine transformation scale parameter is maintained. Compared to ad-hoc detectors, BFAR has the advantage of a specified upper-bound for the false-alarm probability, and better noise handling than CFAR. Repeatability tests show that BFAR yields highly repeatable detections with minimal redundancy. We have conducted simulations to compare the detection and false-alarm probabilities of BFAR with those of three baselines in non-homogeneous noise and varying target sizes. The results show that BFAR outperforms the other detectors. Moreover, We apply BFAR to the use case of radar odometry, and adapt a recent odometry pipeline, replacing its original conservative filtering with BFAR. In this way, we reduce the translation/rotation odometry errors/100 m from 1.3%/0.4(^circ ) to 1.12%/0.38(^circ ), and from 1.62%/0.57(^circ ) to 1.21%/0.32(^circ ), improving translation error by 14.2% and 25% on Oxford and Mulran public data sets, respectively.

Learning effective continuous control policies in high-dimensional systems, including musculoskeletal agents, remains a significant challenge. Over the course of biological evolution, organisms have developed robust mechanisms for overcoming this complexity to learn highly sophisticated strategies for motor control. What accounts for this robust behavioral flexibility? Modular control via muscle synergies, i.e. coordinated muscle co-contractions, is considered to be one putative mechanism that enables organisms to learn muscle control in a simplified and generalizable action space. Drawing inspiration from this evolved motor control strategy, we use physiologically accurate human hand and leg models as a testbed for determining the extent to which a Synergistic Action Representation (SAR) acquired from simpler tasks facilitates learning and generalization on more complex tasks. We find in both cases that SAR-exploiting policies significantly outperform end-to-end reinforcement learning. Policies trained with SAR were able to achieve robust locomotion on a diverse set of terrains (e.g., stairs, hills) with state-of-the-art sample efficiency (4 M total steps), while baseline approaches failed to learn any meaningful behaviors under the same training regime. Additionally, policies trained with SAR on in-hand 100-object manipulation task significantly outperformed (>70% success) baseline approaches (<20% success). Both SAR-exploiting policies were also found to generalize zero-shot to out-of-domain environmental conditions, while policies that did not adopt SAR failed to generalize. Finally, using a simulated robotic hand and humanoid agent, we establish the generality of SAR on broader high-dimensional control problems, solving tasks with greatly improved sample efficiency. To the best of our knowledge, this investigation is the first of its kind to present an end-to-end pipeline for discovering synergies and using this representation to learn high-dimensional continuous control across a wide diversity of tasks. Project website:https://sites.google.com/view/sar-rl

Several applications require that unmanned vehicles, such as UAVs and AUVs, navigate environmental flows. While the flow can improve the vehicle’s efficiency when directed towards the goal, it may also cause feasibility problems when it is against the desired motion and is too strong to be counteracted by the vehicle. This paper proposes the flow-aware fast marching tree algorithm (FlowFMT*) to solve the optimal motion planning problem in generic three-dimensional flows. Our method creates either an optimal path from start to goal or, with a few modifications, a vector field-based policy that guides the vehicle from anywhere in its workspace to the goal. The basic idea of the proposed method is to replace the original neighborhood set used by FMT* with two sets that consider the reachability from/to each sampled position in the space. The new neighborhood sets are computed considering the flow and the maximum speed of the vehicle. Numerical results that compare our methods with the state-of-the-art optimal control solver illustrate the simplicity and correctness of the method.

This paper explores range and bearing angle regulation of a leader–follower using monocular vision. The main challenge is that monocular vision does not directly provide a range measurement. The contribution is a novel concurrent learning (CL) approach, called CL Subtended Angle and Bearing Estimator for Relative pose (CL-SABER), which achieves range regulation without communication, persistency of excitation or known geometry and is demonstrated on a physical, robot platform. A history stack estimates target size which augments the Kalman filter (KF) with a range pseudomeasurement. The target is followed to scale without drift, persistency of excitation requirements, prior knowledge, or additional measurements. Finite excitation is required to achieve parameter convergence and perform steady-state regulation using CL-SABER. Evaluation using simulation and mobile robot experiments in special Euclidean planar space (SE(2)) show that the new method provides stable and consistent range regulation, as demonstrated by the inter-rater reliability, including in noisy and high leader acceleration environments.

Inertial-aided systems require continuous motion excitation among other reasons to characterize the measurement biases that will enable accurate integration required for localization frameworks. This paper proposes the use of informative path planning to find the best trajectory for minimizing the uncertainty of IMU biases and an adaptive traces method to guide the planner towards trajectories that aid convergence. The key contribution is a novel regression method based on Gaussian Process (GP) to enforce continuity and differentiability between waypoints from a variant of the (hbox {RRT}^*) planning algorithm. We employ linear operators applied to the GP kernel function to infer not only continuous position trajectories, but also velocities and accelerations. The use of linear functionals enable velocity and acceleration constraints given by the IMU measurements to be imposed on the position GP model. The results from both simulation and real-world experiments show that planning for IMU bias convergence helps minimize localization errors in state estimation frameworks.

The process-aware source seeking (PASS) problem in flow fields aims to find an informative trajectory to reach an unknown source location while taking the energy consumption in the flow fields into consideration. Taking advantage of the dynamic flow field partition technique, this paper formulates this problem as a task and motion planning (TAMP) problem and proposes a bi-level hierarchical planning framework to decouple the planning of inter-region transition and inner-region trajectory by introducing inter-region junctions. An integrated strategy is developed to enable efficient upper-level planning by investigating the optimal solution of the lower-level planner. In order to leverage the information acquisition and computational burden, a dynamic event-triggered mechanism is introduced to enable asynchronized estimation, region partitioning and re-plans. The proposed algorithm provides guaranteed convergence of the trajectory, and achieves automatic trade-offs of both exploration-exploitation and accuracy-efficiency. Simulations in a highly complicated and realistic ocean surface flow field validate the merits of the proposed algorithm, which demonstrates a significant reduction in computational burden without compromising planning optimality.

This paper proposes an innovative approach for optical flow-based control of micro air vehicles (MAVs), addressing challenges inherent in the nonlinearity of optical flow observables. The proposed incremental nonlinear dynamic inversion (INDI) control scheme employs an efficient data-driven approach to directly estimate the inverse of the time-varying INDI control effectiveness in real-time. This method eliminates the constant effectiveness assumption typically made by traditional INDI methods and reduces the computational burden associated with inverting this variable at each time step. It effectively handles rapidly changing system dynamics, often encountered in optical flow-based control, particularly height-dependent control variables. Stability analysis of the proposed control scheme is conducted, and its robustness and efficiency are demonstrated through both numerical simulations and real-world flight tests. These tests include multiple landings of an MAV on a static, flat surface with several different tracking setpoints, as well as hovering and landings on moving and undulating surfaces. Despite the challenges posed by noisy optical flow estimates and lateral or vertical movements of the landing surfaces, the MAV successfully tracks or lands on the surface with an exponential decay of both height and vertical velocity almost simultaneously, aligning with the desired performance.

In this paper, we present models and planning algorithms to slide an object on a planar surface via frictional patch contact made with its top surface, whether the surface is horizontal or inclined. The core of our approach is the asymmetric dual limit surfaces model that determines slip boundary conditions for both the top and support patch contacts made with the object. This model enables us to compute a range of twists that can keep the object in sticking contact with the robot end-effector while slipping on the supporting plane. Based on these constraints, we derive a planning algorithm to slide objects with only top contact to arbitrary goal poses without slippage between end effector and the object. We fit the proposed model and demonstrate its predictive accuracy on a variety of object geometries and motions. We also evaluate the planning algorithm over a variety of objects and goals, demonstrating an orientation error improvement of 90% when compared to methods naive to linear path planners. For more results and information, please visit https://www.mmintlab.com/dual-limit-surfaces/.

Trust is a crucial factor for effective human–robot teaming. Existing literature on trust modeling predominantly focuses on dyadic human-autonomy teams where one human agent interacts with one robot. There is little, if not no, research on trust modeling in teams consisting of multiple human and robotic agents. To fill this important research gap, we present the Trust Inference and Propagation (TIP) model to model and estimate human trust in multi-human multi-robot teams. In a multi-human multi-robot team, we postulate that there exist two types of experiences that a human agent has with a robot: direct and indirect experiences. The TIP model presents a novel mathematical framework that explicitly accounts for both types of experiences. To evaluate the model, we conducted a human-subject experiment with 15 pairs of participants ((N=30)). Each pair performed a search and detection task with two drones. Results show that our TIP model successfully captured the underlying trust dynamics and significantly outperformed a baseline model. To the best of our knowledge, the TIP model is the first mathematical framework for computational trust modeling in multi-human multi-robot teams.