With the increasing requirement for agile and efficient controllers in safety-critical scenarios, controllers that exhibit both agility and safety are attracting attention, especially in the aerial robotics domain. Th...
详细信息
With the increasing requirement for agile and efficient controllers in safety-critical scenarios, controllers that exhibit both agility and safety are attracting attention, especially in the aerial robotics domain. This paper focuses on the safety issue of Reinforcement Learning (RL)-based control for agile quadrotor flight in restricted environments. To this end, we propose a unified Adaptive Safety Predictive Corrector (ASPC) to certify each output action of the RL-based controller in real-time, ensuring its safety while maintaining agility. Specifically, we develop the ASPC as a finite-horizon optimal control problem, formulated by a variant of Model Predictive control (MPC). Given the safety constraints determined by the restricted environment, the objective of minimizing loss of agility can be optimized by reducing the difference between the actions of RL and ASPC. As the safety constraints are decoupled from the RL-based control policy, the ASPC is plug-and-play and can be incorporated into any potentially unsafe controllers. Furthermore, an online adaptive regulator is presented to adjust the safety bounds of the state constraints with respect to the environment changes, extending the proposed ASPC to different restricted environments. Finally, simulations and real-world experiments are demonstrated in various restricted environments to validate the effectiveness of the proposed ASPC. IEEE
Clarifying the relationship between stress sensitivities of permeability and porosity is of great significance in guiding underground resource *** and more studies focus on how to construct stress sensitivity models t...
详细信息
Clarifying the relationship between stress sensitivities of permeability and porosity is of great significance in guiding underground resource *** and more studies focus on how to construct stress sensitivity models to describe the relationship and obtain a comprehensive stress sensitivity of porous ***,the limitations of elastic deformation calculation and incompleteness of considered tortuosity sensitivity lead to the fact that the existing stress sensitivity models are still unsatisfactory in terms of accuracy and ***,a more accurate and generic stress sensitivity model considering elastic-structural deformation of capillary cross-section and tortuosity sensitivity is proposed in this *** elastic deformation is derived from the fractal scaling model and Hooke's *** the effects of elastic-structural deformation on tortuosity sensitivity,an empirical formula is proposed,and the conditions for its applicability are *** predictive performance of the proposed model for the permeability-porosity relationships is validated in several sets of publicly available experimental *** experimental data are from different rocks under different pressure *** mean and standard deviation of relative errors of predicted stress sensitivity with respect to experimental data are 2.63%and 1.91%.Compared with other models,the proposed model has higher accuracy and better predictive generalization *** is also found that the porosity sensitivity exponent a,which can describe permeability-porosity relationships,is 2 when only elastic deformation is considered.a decreases from 2 when structural deformation is also *** addition,a may be greater than 3 due to the increase in tortuosity sensitivity when tortuosity sensitivity is considered even if the rock is not fractured.
This paper proposes an improved high-precision 3D semantic mapping method for indoor scenes using RGB-D *** current semantic mapping algorithms suffer from low semantic annotation accuracy and insufficient real-time *...
详细信息
This paper proposes an improved high-precision 3D semantic mapping method for indoor scenes using RGB-D *** current semantic mapping algorithms suffer from low semantic annotation accuracy and insufficient real-time *** address these issues,we first adopt the Elastic Fusion algorithm to select key frames from indoor environment image sequences captured by the Kinect sensor and construct the indoor environment space ***,an indoor RGB-D image semantic segmentation network is proposed,which uses multi-scale feature fusion to quickly and accurately obtain object labeling information at the pixel level of the spatial point cloud ***,Bayesian updating is used to conduct incremental semantic label fusion on the established spatial point cloud *** also employ dense conditional random fields(CRF)to optimize the 3D semantic map model,resulting in a high-precision spatial semantic map of indoor *** results show that the proposed semantic mapping system can process image sequences collected by RGB-D sensors in real-time and output accurate semantic segmentation results of indoor scene images and the current local spatial semantic ***,it constructs a globally consistent high-precision indoor scenes 3D semantic map.
Traditional rigid-body in-pipe robots usually have complex and heavy structures with limited flexibility and *** soft in-pipe robots have great improvements in flexibility,they still have manufacturing difficulties du...
详细信息
Traditional rigid-body in-pipe robots usually have complex and heavy structures with limited flexibility and *** soft in-pipe robots have great improvements in flexibility,they still have manufacturing difficulties due to their reliance on high-performance soft *** structure is a kind of self-stressed spatial structure consisting discrete rigid struts connected by a continuous net of tensional flexible strings,which combines the advantages of both rigid structures and soft *** applying tensegrity structures into robotics,this paper proposes a novel worm-like tensegrity robot for moving inside ***,a robot module capable of body deformation is designed based on the concept of tensegrity and its deformation performance is ***,the optimal parameters of the module are obtained based on the tensegrity *** deformation ability of the tensegrity module is tested ***,the worm-like tensegrity robot that can crawl inside pipes is developed by connecting three modules in *** performance and load capacity are tested on the prototype of the worm-like tensegrity robot by experiments of moving in horizontal pipe,vertical pipe,and elbow *** results demonstrate the effectiveness of the proposed design and suggest that the robot has high compliance,mobility,and adaptability although with simple structure and low cost.
The paper proposes an approach to position-force control in the underwater vehicle-manipulator systems. There are two different strategies to realize position-force controlsystems: through a decoupled or coupled cont...
详细信息
This paper applies the MIMO NARX neural model to identify AUV with six degrees of freedom. Strongly nonlinear dependencies are modeled using a MIMO NARX model trained using «input-output» experimental data. ...
详细信息
To address the locomotion control issue of quadruped guide robots across multiple terrains, a teacher-student framework is adopted to learn the multi-gait locomotion policy. Specifically, the interaction forces betwee...
详细信息
To achieve precise localization,autonomous vehicles usually rely on a multi-sensor perception system surrounding the mobile *** is a time-consuming process,and mechanical distortion will cause extrinsic calibration **...
详细信息
To achieve precise localization,autonomous vehicles usually rely on a multi-sensor perception system surrounding the mobile *** is a time-consuming process,and mechanical distortion will cause extrinsic calibration ***,we propose a lidar-visual-inertial odometry,which is combined with an adapted sliding window mechanism and allows for online nonlinear optimization and extrinsic *** the adapted sliding window mechanism,spatial-temporal alignment is performed to manage measurements arriving at different *** nonlinear optimization with online calibration,visual features,cloud features,and inertial measurement unit(IMU)measurements are used to estimate the ego-motion and perform extrinsic *** experiments were carried out on both public datasets and real-world *** indicate that the proposed system outperforms state-of-the-art open-source methods when facing challenging sensor-degenerating conditions.
Deep neural networks (DNNs) are acknowledged as vulnerable to adversarial attacks while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates. For query-efficiency, s...
详细信息
Micro-motion augmentation of macro-motion continuum robot can largely enhance its micro-operation capability during surgery. However, most existing micro-motion continuum robots have non-compact mechanical structure o...
详细信息
暂无评论