This work presents a first-principles, low-order model of the sagittal-plane swimming dynamics of a bottlenose dolphin. The model captures key features of cetacean swimming, namely lift-based propulsion, unsteady hydr...
This work presents a first-principles, low-order model of the sagittal-plane swimming dynamics of a bottlenose dolphin. The model captures key features of cetacean swimming, namely lift-based propulsion, unsteady hydrodynamics, fluke flexibility, and body posture. The model is used to estimate steady-state swimming kinematics and kinetics at a range of speeds, which are then compared to published estimates from swimming animals.
Rod-driven soft robots (RDSR) with a well-balanced performance in terms of perception, precision, and intelligence have a great potential for application. Mathematical description and predicted sensing of deformable s...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
Rod-driven soft robots (RDSR) with a well-balanced performance in terms of perception, precision, and intelligence have a great potential for application. Mathematical description and predicted sensing of deformable soft bodies are crucial to achieve controllable and intelligent behaviors of these robots. In this work, we propose a kinetostatic model for RDSR embedded with co-located sensors based on the Geometric Variable Strain (GVS) approach where local deformations, actuation lengths and external interactions are included. This approach allows us to estimate the shape of RDSR and predict the strain variation of soft bodies under internal and external interactions. Simulations and experimental results show that tip position errors are not greater than 1.8% with respect to the whole body length under different loads (0, 100, 200, 300 gf). The maximum error of predicted sensor length change is up to 2 mm and its percentage relative to the actual length does not exceed 4%. The results demonstrate the accuracy and effectiveness of the proposed model.
In this paper, we propose a system that enables visualization under the situation of scattering media such as fog and smoke by Peplography which is scattering media removal system, on a small GPU machine. Compared to ...
详细信息
This paper proposes MambaST, a plug-and-play cross-spectral spatial-temporal fusion pipeline for efficient pedestrian detection. Several challenges exist for pedestrian detection in autonomous driving applications. Fi...
详细信息
ISBN:
(数字)9798331505929
ISBN:
(纸本)9798331505936
This paper proposes MambaST, a plug-and-play cross-spectral spatial-temporal fusion pipeline for efficient pedestrian detection. Several challenges exist for pedestrian detection in autonomous driving applications. First, it is difficult to perform accurate detection using RGB cameras under dark or low-light conditions. Cross-spectral systems must be developed to integrate complementary information from multiple sensor modalities, such as thermal and visible cameras, to improve the robustness of the detections. Second, pedestrian detection models are latency-sensitive. Efficient and easy-to-scale detection models with fewer parameters are highly desirable for real-time applications such as autonomous driving. Third, pedestrian video data provides spatial-temporal correlations of pedestrian movement. It is beneficial to incorporate temporal as well as spatial information to enhance pedestrian detection. This work leverages recent advances in the state space model (Mamba) and proposes a novel Multi-head Hierarchical Patching and Aggregation (MHHPA) structure to extract both fine-grained and coarse-grained information from both RGB and thermal imagery. Experimental results show that the proposed MHHPA is an effective and efficient alternative to a Transformer model for cross-spectral pedestrian detection. Our proposed model also achieves superior performance on small-scale pedestrian detection. The code is available at https://***/XiangboGaoBarry/MambaST
Selective laser melting(SLM)or Laser-based powder bed fusion(LBPF)is gaining much attention for the fabrication of novel materials with complex shapes,improved functionalities,and *** attempt has been made to fabricat...
详细信息
Selective laser melting(SLM)or Laser-based powder bed fusion(LBPF)is gaining much attention for the fabrication of novel materials with complex shapes,improved functionalities,and *** attempt has been made to fabricate hard and brittle silicon via SLM in the absence of any *** different powder batches were used,where one of the powder batches has 0.3wt%Fe and the other batch with 0.02wt%*** parameter optimization process shows that the SLM Si samples were successfully fabricated from the powders with the minor addition of *** deliberate addition of Fe facilitates heterogeneous nucleation of Si and aids in absorbing the laser energy beam more *** Si samples with 98.5%theoretical density were fabricated with a hardness of around 10.65±40 *** experimental results show that SLM can successfully fabricate Si without cracks and with near theoretical density(of 99%)and complex shapes,which opens their use in wider industrial applications.
The process of educating and learning about the automotive industry is still ongoing, and one of the most effective techniques is the provision of direct practice. Such a system is regarded as effective, albeit with c...
The process of educating and learning about the automotive industry is still ongoing, and one of the most effective techniques is the provision of direct practice. Such a system is regarded as effective, albeit with certain downsides. One of them is the restricted area and time required to conduct the exercise, as well as the significant risk of accidents during vehicle engine assembly. Based on these justifications, Vehicle Engine Assembly Simulation with Virtual Reality (VR) Technology is now available as an alternate means of educating students about the automotive industry, particularly car engine assembly. This concept employs a virtual environment that allows users to perceive the automobile world in real time through an immersive experience. VR allows users to directly disassemble automobile engines. This virtual reality application was created utilizing the Oculus Quest 2 platform and the Unity Game Engine.
Biodegradable food packaging gains a lot of significance for the sake of environment, and increased prohibition of using plastic package. Further, the functionality of sensing food status is in great importance becaus...
详细信息
Soft robotic systems necessitate accurate and reliable sensor readings to detect environmental interactions and provide precise feedback for control. To be effective, soft sensors must exhibit sensitivity, reliability...
Soft robotic systems necessitate accurate and reliable sensor readings to detect environmental interactions and provide precise feedback for control. To be effective, soft sensors must exhibit sensitivity, reliability, repeatability, and flexibility. A versatile approach to sensing for soft robots uses soft air-filled deformable structures with pressure transducers to detect pressure changes due to applied forces. However, the common approach of employing one pressure transducer per sensing chamber limits the scalability of this sensing approach (e.g., for large arrays able to detect touch at many locations). Here we present an approach to the design of pneumatic sensor arrays that reduces the number of required transducers. We develop mathematical models to analyze the pressure variations within the sensor arrays in response to applied forces at various locations. We also introduce a method of rapidly fabricating sensor arrays by laminating elastomeric sheets patterned with laser-cut sacrificial layers. We then use our model to optimize the geometry of the sensors and evaluate the results experimentally. Finally, we devise an algorithm capable of determining the location of multiple touches anywhere within the sensor array. This work represents a step towards the practical application of soft pneumatic sensors, particularly for robotic sensing and haptic devices, enhancing the safety of human-robot interactions.
Unmanned aerial vehicles (UAVs) are widely used in various industries. The present study focused on the optimization of the configuration of the vertical electric ducted fans (EDFs) of UAVs to enhance the vertical tak...
详细信息
Deep Reinforcement Learning (DRL), combined with demonstration data, has progressed in developing manipulation policies. However, the practical collection of ample high-quality demonstrations is timeconsuming, and dem...
详细信息
ISBN:
(数字)9798350355369
ISBN:
(纸本)9798350355376
Deep Reinforcement Learning (DRL), combined with demonstration data, has progressed in developing manipulation policies. However, the practical collection of ample high-quality demonstrations is timeconsuming, and demonstrations generated by humans may not perfectly align with the operational demands of robots. Our study suggests that RL agents in manipulation tasks are acutely sensitive to demonstration quality in both online and offline environments. Utilizing low-quality or limited demonstrations to enhance RL policy development remains a significant challenge. To address these concerns, we propose TD3+Smooth BC, an enhancement of TD3+BC [1] and TD3fG [2]. This algorithm ensures a smooth transition from learning through expert demonstrations to learning from experience, incorporating prior knowledge while mitigating negative demonstration impacts. In the offline setting, TD3+Smooth BC adjusts the balance between imitation and Q-value maximization dynamically, effectively utilizing human demonstrations for efficient policy learning. The algorithm demonstrates marked improvements in the Adroit manipulator and MuJoCo tasks, even with limited demonstrations of varying quality.
暂无评论