Point clouds are often sparse and incomplete, which imposes difficulties for real-world applications. Existing shape completion methods tend to generate rough shapes without fine-grained details. ...Considering this, we introduce a two-branch network for shape completion. The first branch is a cascaded shape completion sub-network to synthesize complete objects, where we propose to use the partial input together with the coarse output to preserve the object details during the dense point reconstruction. The second branch is an auto-encoder to reconstruct the original partial input. The two branches share a same feature extractor to learn an accurate global feature for shape completion. Furthermore, we propose two strategies to enable the training of our network when ground truth data are not available. This is to mitigate the dependence of existing approaches on large amounts of ground truth training data that are often difficult to obtain in real-world applications. Additionally, our proposed strategies are also able to improve the reconstruction quality for fully supervised learning. We verify our approach in self-supervised, semi-supervised and fully supervised settings with superior performances. Quantitative and qualitative results on different datasets demonstrate that our method achieves more realistic outputs than state-of-the-art approaches on the point cloud completion task.
While brain-computer interfaces (BCIs) can provide communication to people who are locked-in, they suffer from a very low information transfer rate. Further, using a BCI requires a concentration ...effort and using it continuously can be tiring. The brain controlled wheelchair (BCW) described in this paper aims at providing mobility to BCI users despite these limitations, in a safe and efficient way. Using a slow but reliable P300 based BCI, the user selects a destination amongst a list of predefined locations. While the wheelchair moves on virtual guiding paths ensuring smooth, safe, and predictable trajectories, the user can stop the wheelchair by using a faster BCI. Experiments with nondisabled subjects demonstrated the efficiency of this strategy. Brain control was not affected when the wheelchair was in motion, and the BCW enabled the users to move to various locations in less time and with significantly less control effort than other control strategies proposed in the literature.
In order to satisfy the requirement of the automatic ultrasonic strengthening of an aviation blade surface, this paper puts forward a robotic compliance control strategy of contact force for ...ultrasonic surface strengthening. By building the force/position control method for robotic ultrasonic surface strengthening., the compliant output of the contact force is achieved by using the robot's end-effector (compliant force control device). Based on the control model of the end-effector obtained from experimental determination, a fuzzy neural network PID control is used to optimize the compliance control system, which improves the adjustment accuracy and tracking performance of the system. An experimental platform is built to verify the effectiveness and feasibility of the compliance control strategy for the robotic ultrasonic strengthening of an aviation blade surface. The results demonstrate that the proposed method maintains the compliant contact between the ultrasonic strengthening tool and the blade surface under multi-impact and vibration conditions.
We present the design of a universal gripper based on the principle of liquid jamming. The phase change behavior of a mineral oil subjected to cooling is used for adaptive gripping and release of ...objects. The mineral oil is enclosed in a soft, compliant membrane molded into a spherical shape. The membrane with the liquid easily adapts to the shape of the object to be picked up. A thermoelectric cooling system is designed with a conductive spreader immersed in the oil to quickly cool the liquid held in a membrane. Once the membrane gripper conforms to the shape of the object partially enclosing it, the liquid is cooled below the phase change temperature, thus freezing the liquid and hardening the gripper around the object and effectively gripping it. We describe the design methodology of the gripper, part selection, and mechanical design. A proprietary controller developed by Venture Corporation is used for controlling the TEC module and the controller is based on a simple PID optimized using Ziegler–Nichols tuning for the P, I, and D values. The hardware is evaluated and the basic gripping functions on different odd-shaped objects are demonstrated. An invention disclosure has been submitted to the NUS IP office (ILO).
The learning and aggregation of multi-scale features are essential in empowering neural networks to capture the fine-grained geometric details in the point cloud upsampling task. Most existing ...approaches extract multi-scale features from a point cloud of a fixed resolution, hence obtain only a limited level of details. Though an existing approach aggregates a feature hierarchy of different resolutions from a cascade of upsampling sub-network, the training is complex with expensive computation. To address these issues, we construct a new point cloud upsampling pipeline called BIMS-PU that integrates the feature pyramid architecture with a bi-directional up and downsampling path. Specifically, we decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors. The multi-scale features are naturally produced in a parallel manner and aggregated using a fast feature fusion method. Supervision signal is simultaneously applied to all upsampled point clouds of different scales. Moreover, we formulate a residual block to ease the training of our model. Extensive quantitative and qualitative experiments on different datasets show that our method achieves superior results to state-of-the-art approaches. Last but not least, we demonstrate that point cloud upsampling can improve robot perception by ameliorating the 3D data quality.
As autonomous vehicles begin venturing on the urban road, rational decision making is essential for driving safety and efficiency. This paper presents a situation-aware decision making algorithm for ...autonomous driving on urban road. Specifically, an urban road situation model is proposed first for proper environment representation, thereafter the situation-aware decision making problem is modeled as a Partially Observable Markov Decision Process (POMDP) and solved in an online manner. The proposed algorithm has been extensively evaluated, which is general enough for autonomous driving in various urban road scenarios, including leader following, collision avoidance and traffic negotiation at both T-junction and roundabout.
•The permittivity, capacitance, dielectric loss and other indexes are analyzed.•The dielectric properties are characterized by Cole-Cole model.•The dependence of permittivity and polarization ...relaxation behavior are revealed.
In this study, the dielectric constants of VHB4905 and VHB4910 are measured systematically, and the capacitance, edge capacitance, dielectric loss and dielectric loss factor are analyzed. The dielectric properties are revealed from the microstructure, and the Cole-Cole model is used to characterize the dielectric properties. The results show that the dielectric constant is very sensitive to the frequency dependence, but it is sensitive to the real and imaginary parts from 102 Hz to 106 Hz. The relative errors of their permittivity are small, when the edge effect is not taken into account. At high frequency, the orientation movement of the polar group on the side chain of VHB acrylic leads to the decrease of the molecular polarizability, and the energy consumption of electric dipole, shift polarization and turn polarization leads to the decrease of the dielectric constant and the increase of the dielectric loss. The fitting correlation coefficients of dielectric constant for VHB4905 and VHB4910 are high, which describe the polarization relaxation behavior of VHB acrylic acid. The research in this paper is helpful to understand the electrical characteristics of acrylic acid, and provides a basis for the design and control of dielectric elastomer actuator.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
G<inline-formula><tex-math notation="LaTeX">_{2}</tex-math></inline-formula>-continuous trajectories are crucial for vehicles under non-holonomic dynamic constraints to run smoothly. In this paper, ...we present a path smoothing method based on piece-wise quadratic Bézier curves, which can fit a set of sequential 2D collision-free path points generated by a higher-level path planner. The generated trajectories are G<inline-formula><tex-math notation="LaTeX">_{2}</tex-math></inline-formula>-continuous except at the inflection points, and points of local curvature maxima appear exactly at path points and nowhere else. The local curvature control ensures that the trajectories keep high fidelity with the original paths, thus maintaining key properties of the original paths, such as free collision and gentle turns. Furthermore, we develop a joint optimization method for both fidelity and continuity, which has an efficient analytical solution for each iteration. Extensive experiments in both simulated and real scenarios validate that 1) the smoothed trajectories can deviate less than 10 cm from the original paths, 2) the average curvature differences at junctures are under 1e-4 (1/m), 3) the smoothing time reduced by about 50% versus high-order bézier methods, showing superior performance of the proposed method in terms of fidelity, continuity, efficiency, and practicability.
Trajectory planning is a critical component in autonomous vehicles directly responsible for driving safety and efficiency during deployment. The ability to find the optimal trajectory in real-time is ...critical for autonomous driving. This paper presents a novel general framework using the Fast Iterative Search and Sampling (FISS) strategy for sampling-based trajectory planning, which can find the optimal trajectory from an enormous number of candidates with high efficiency in real-time. Specifically, before generating any trajectories, the proposed method utilizes historical planning results as prior information in heuristics to estimate the cost distribution over the sampling space. On this basis, the Fast Iterative Search and Sampling strategy is employed to explore the sampling space for possible candidates and generate trajectories for verification during the search process. Experimental results show that our method can significantly outperform existing frameworks by order of magnitude in planning efficiency while ensuring safety and maintaining high accuracy.
Autonomous driving in rainy conditions remains a big challenge. One of the issues is sensor degradation. LiDAR is commonly used in autonomous driving systems to perceive and understand surrounding ...environments. However, LiDAR performance can be degraded by rain, thereby influencing other system performance (e.g., perception or localization). Therefore, knowing how much degradation exists in current LiDAR measurements is necessary. Most existing methods can only measure LiDAR degradation in controlled environments (e.g., a chamber with simulated rain); how to quantify LiDAR degradation in dynamic environments while the autonomous vehicle is moving is still a difficult problem. In this work, we propose a novel approach to address this problem using an anomaly detection method. Our method has been evaluated on simulated and real-world data. Experimental results demonstrate the effectiveness of our method to capture LiDAR degradation and yield reasonable degradation estimations. Our experimental data and codes are accessible from http://rain.smart.mit.edu/smartrain/.
PDF
