This paper presents an off-policy Gaussian Predictive Control (GPC) framework aimed at solving optimal control problems with a smaller computational footprint, thereby facilitating real-time applicability while ensuri...
详细信息
ISBN:
(数字)9798350382655
ISBN:
(纸本)9798350382662
This paper presents an off-policy Gaussian Predictive Control (GPC) framework aimed at solving optimal control problems with a smaller computational footprint, thereby facilitating real-time applicability while ensuring critical safety considerations. The proposed controller imitates classical control methodologies by modeling the optimization process through a Gaussian process and employs Gaussian Process Regression to learn from the Model Predictive Control (MPC) algorithm. Notably, the Gaussian Process setup does not incorporate a built-in model, enhancing its applicability to a broad range of control problems. We applied this framework experimentally to a differential drive mobile robot, tasking it with trajectory tracking and obstacle avoidance. Leveraging the off-policy aspect, the controller demonstrated adaptability to diverse trajectories and obstacle behaviors. Simulation experiments confirmed the effectiveness of the proposed GPC method, emphasizing its ability to learn the dynamics of optimal control strategies. Consequently, our findings highlight the significant potential of off-policy Gaussian Predictive Control in achieving real-time optimal control for handling of robotic systems in safety-critical scenarios.
This paper introduces a deep learning-based semantic segmentation framework tailored for robotic apple harvesting, leveraging synthetic data generated within a 3D simulated apple orchard. The proposed simulation envir...
详细信息
ISBN:
(数字)9798350361070
ISBN:
(纸本)9798350361087
This paper introduces a deep learning-based semantic segmentation framework tailored for robotic apple harvesting, leveraging synthetic data generated within a 3D simulated apple orchard. The proposed simulation environment replicates real-world scenarios, encompassing challenges such as occlusion, variety in apple types, and changes in lighting conditions. This approach eliminates the extensive costs and complexities associated with collecting real-world datasets, particularly in unpredictable agricultural settings. The synthetic dataset, rendered from perspectives consistent with a robotic harvester's camera in the Gazebo physics engine, provides a comprehensive range of scenarios for robust model training. For validation, we deploy U-Net, a fully convolutional neural network, emphasizing its adaptability to domain shifts between synthetic and real-world data. By integrating strategies such as domain adaptation, data augmentation, and the inclusion of pre-trained ResNet-50 encoders in the U-Net framework, we demonstrate superior performance in detecting and segmenting apples in diverse real-world conditions compared to standard U-Net models and traditional computer vision techniques. The results highlight the potential of synthetic data in deep learning-based semantic segmentation, offering a cost-effective and scalable solution when real-world data is limited or hard to collect.
Optimization methods for long-horizon, dynamically feasible motion planning in robotics tackle challenging nonconvex and discontinuous optimization problems. Traditional methods often falter due to the nonlinear chara...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Optimization methods for long-horizon, dynamically feasible motion planning in robotics tackle challenging nonconvex and discontinuous optimization problems. Traditional methods often falter due to the nonlinear characteristics of these problems. We introduce a technique that utilizes learned representations of the system, known as Polytopic Action Sets, to efficiently compute long-horizon trajectories. By employing a suitable sequence of Polytopic Action Sets, we transform the long-horizon dynamically feasible motion planning problem into a Linear program. This reformulation enables us to address motion planning as a Mixed Integer Linear program (MILP). We demonstrate the effectiveness of a Polytopic Action-Set and Motion Planning (PAAMP) approach by identifying swing-up motions for a torque-constrained pendulum as fast as 0.75 milliseconds. This approach is well-suited for solving complex motion planning and long-horizon Constraint Satisfaction Problems (CSPs) in dynamic and underactuated systems such as legged and aerial robots.
3D point clouds enhanced the robot’s ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection and scene understanding. The perform...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
3D point clouds enhanced the robot’s ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection and scene understanding. The performance of these tasks, though, heavily relies on the quality of data input, as incomplete can lead to poor results and failure cases. Recent training loss functions designed for deep learning-based point cloud completion, such as Chamfer distance (CD) and its variants (e.g. HyperCD [1]), imply a good gradient weighting scheme can significantly boost performance. However, these CD-based loss functions usually require data-related parameter tuning, which can be time-consuming for data-extensive tasks. To address this issue, we aim to find a family of weighted training losses (weighted CD) that requires no parameter tuning. To this end, we propose a search scheme, Loss Distillation via Gradient Matching, to find good candidate loss functions by mimicking the learning behavior in backpropagation between HyperCD and weighted CD. Once this is done, we propose a novel bilevel optimization formula to train the backbone network based on the weighted CD loss. We observe that: (1) with proper weighted functions, the weighted CD can always achieve similar performance to HyperCD, and (2) the Landau weighted CD, namely Landau CD, can outperform HyperCD for point cloud completion and lead to new state-of-the-art results on several benchmark datasets. Our demo code is available at https://***/Zhang-VISLab/IROS2024-LossDistillationWeightedCD.
Compositionality is a critical aspect of scalable system design. Here, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for Reinforcemen...
Compositionality is a critical aspect of scalable system design. Here, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for Reinforcement Learning focuses on reaching a satisfying absorbing state in environments with discrete action spaces, but does not support composable safety (i.e., avoidance) constraints. We provide three contributions: i) introduce two distinct notions of compositional safety semantics; ii) show how to enforce either safety semantics, prove correctness, and analyze the trade-offs between the two safety notions; and iii) extend Boolean composition from discrete action spaces to continuous action spaces. We demonstrate these techniques using modified versions of value iteration in a grid world, Deep Q-Network (DQN) in a grid world with image observations, and Twin Delayed DDPG (TD3) in a continuous-observation and continuous-action Bullet physics environment.
Per- and polyfluoroalkyl substances (PFAS) are a group of chemicals used for their impressive stability, a property which has also led them to be found polluting virtually every sector of the environment-including our...
详细信息
ISBN:
(数字)9798350309652
ISBN:
(纸本)9798350309669
Per- and polyfluoroalkyl substances (PFAS) are a group of chemicals used for their impressive stability, a property which has also led them to be found polluting virtually every sector of the environment-including our own bodies. Presently, our ability to destroy PFAS is limited largely to incineration, whose products and side effects are poorly understood. Research on PFAS incineration is constrained by high experimental costs and difficulty in accurately measuring reaction products. This presents an opportunity for computer simulation and machine learning to provide valuable assistance. In this study, three kinds of thermal PFAS decomposition are simulated. Further, to broaden physical understanding of PFAS incineration products, a recent in-house machine learning model for predicting the octanol-water partition coefficient (LogP) of chemicals is improved and applied to simulation results. A decrease in LogP is observed in all treatments, with the most dramatic effect (-2 average LogP) observed in oxidative pyrolysis.
Spectroscopic photoacoustic (sPA) imaging uses multiple wavelengths to differentiate and quantify chromophores based on their unique optical absorption spectra. This technique has been widely applied in areas such as ...
Aerial transportation using quadrotors with cable-suspended payloads holds great potential for applications in disaster response, logistics, and infrastructure maintenance. However, their hybrid and underactuated dyna...
详细信息
The interaction between an asymmetric (bevel) tipped needle and the surrounding tissue in image-guided percutaneous interventions, such as in prostate needle biopsy, can result in the deflection of the needle tip and ...
详细信息
Automation in surgical robotics has the potential to improve patient safety and surgical efficiency, but it is difficult to achieve due to the need for robust perception algorithms. In particular, 6D pose estimation o...
详细信息
ISBN:
(数字)9798350384574
ISBN:
(纸本)9798350384581
Automation in surgical robotics has the potential to improve patient safety and surgical efficiency, but it is difficult to achieve due to the need for robust perception algorithms. In particular, 6D pose estimation of surgical instruments is critical to enable the automatic execution of surgical maneuvers based on visual feedback. In recent years, supervised deep learning algorithms have shown increasingly better performance at 6D pose estimation tasks; yet, their success depends on the availability of large amounts of annotated data. In household and industrial settings, synthetic data, generated with 3D computer graphics software, has been shown as an alternative to minimize annotation costs of 6D pose datasets. However, this strategy does not translate well to surgical domains as commercial graphics software have limited tools to generate images depicting realistic instrument-tissue interactions. To address these limitations, we propose an improved simulation environment for surgical robotics that enables the automatic generation of large and diverse datasets for 6D pose estimation of surgical instruments. Among the improvements, we developed an automated data generation pipeline and an improved surgical scene. To show the applicability of our system, we generated a dataset of 7.5k images with pose annotations of a surgical needle that was used to evaluate a state-of-the-art pose estimation network. The trained model obtained a mean translational error of 2.59mm on a challenging dataset that presented varying levels of occlusion. These results highlight our pipeline’s success in training and evaluating novel vision algorithms for surgical robotics applications.
暂无评论