arXiv subjects

Tianyuan Liu

Publications and source records attributed to Tianyuan Liu.

24 records · Page 2Linked to original sources

arXiv2023

Rotating Objects via In-Hand Pivoting using Vision, Force and Touch

We propose a robotic manipulation system that can pivot objects on a surface using vision, wrist force and tactile sensing. We aim to control the rotation of an object around the grip point of a parallel gripper by allowing rotational slip, while maintaining a desired wrist force profile. Our approach runs an end-effector position controller and a gripper width controller concurrently in a closed loop. The position controller maintains a desired force using vision and wrist force. The gripper controller uses tactile sensing to keep the grip firm enough to prevent translational slip, but loose enough to induce rotational slip. Our sensor-based control approach relies on matching a desired force profile derived from object dimensions and weight and vision-based monitoring of the object pose. The gripper controller uses tactile sensors to detect and prevent translational slip by tightening the grip when needed. Experimental results where the robot was tasked with rotating cuboid objects 90 degrees show that the multi-modal pivoting approach was able to rotate the objects without causing lift or slip, and was more energy-efficient compared to using a single sensor modality and to pick-and-place. While our work demonstrated the benefit of multi-modal sensing for the pivoting task, further work is needed to generalize our approach to any given object.

cs.RO↗

arXiv2023

Divide and Conquer in Video Anomaly Detection: A Comprehensive Review and New Approach

Video anomaly detection is a complex task, and the principle of "divide and conquer" is often regarded as an effective approach to tackling intricate issues. It's noteworthy that recent methods in video anomaly detection have revealed the application of the divide and conquer philosophy (albeit with distinct perspectives from traditional usage), yielding impressive outcomes. This paper systematically reviews these literatures from six dimensions, aiming to enhance the use of the divide and conquer strategy in video anomaly detection. Furthermore, based on the insights gained from this review, a novel approach is presented, which integrates human skeletal frameworks with video data analysis techniques. This method achieves state-of-the-art performance on the ShanghaiTech dataset, surpassing all existing advanced methods.

cs.CV↗

arXiv2023

Human Kinematics-inspired Skeleton-based Video Anomaly Detection

Previous approaches to detecting human anomalies in videos have typically relied on implicit modeling by directly applying the model to video or skeleton data, potentially resulting in inaccurate modeling of motion information. In this paper, we conduct an exploratory study and introduce a new idea called HKVAD (Human Kinematic-inspired Video Anomaly Detection) for video anomaly detection, which involves the explicit use of human kinematic features to detect anomalies. To validate the effectiveness and potential of this perspective, we propose a pilot method that leverages the kinematic features of the skeleton pose, with a specific focus on the walking stride, skeleton displacement at feet level, and neck level. Following this, the method employs a normalizing flow model to estimate density and detect anomalies based on the estimated density. Based on the number of kinematic features used, we have devised three straightforward variant methods and conducted experiments on two highly challenging public datasets, ShanghaiTech and UBnormal. Our method achieves good results with minimal computational resources, validating its effectiveness and potential.

cs.CV↗

arXiv2023

A Non-topological Extension of Bending-immune Valley Topological Edge States

Breaking parity (P) symmetry in C$_6$ symmetric crystals is a common routine to implement a valley-topological phase. At an interface between two crystals of opposite valley phases, the so-called valley topological edge states emerge, and they have been proven useful for wave transport with robustness against 120$^\circ$ bending and a certain level of disorder. However, whether these attractive transport features are bound with the valley topology or due to topological-irrelevant mechanisms remains unclear. In this letter, we discuss this question by examining transport properties of photonic edge states with varied degrees of the P-breaking that tune the valley topology, and reveal that the edge states preserve their transport robustness insensitive to the topology even when the P-symmetry is recovered. Instead, a unique modal character of the edge states -- with localized momentum hotspots around high-symmetric $K$ ($K'$) points -- is recognized to play the key role, which only concerns the existence of the valleys in the bulk band structures, and has no special requirement on the topology. The "non-topological" notion of valley edge states is introduced to conceptualize this modal character, leading to a coherent understanding of bending immunity in a range of edge modes implemented in C$_3$ symmetric crystals -- such as valley topological edge states, topological edge states of 2D Zak phase, topological-trivial edge states and so on, and to new designs in general rhombic lattices -- with exemplified bending angle as large as 150$^\circ$.

physics.optics↗

arXiv2023

How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement

Imitation learning aims to mimic the behavior of experts without explicit reward signals. Passive imitation learning methods which use static expert datasets typically suffer from compounding error, low sample efficiency, and high hyper-parameter sensitivity. In contrast, active imitation learning methods solicit expert interventions to address the limitations. However, recent active imitation learning methods are designed based on human intuitions or empirical experience without theoretical guarantee. In this paper, we propose a novel active imitation learning framework based on a teacher-student interaction model, in which the teacher's goal is to identify the best teaching behavior and actively affect the student's learning process. By solving the optimization objective of this framework, we propose a practical implementation, naming it AdapMen. Theoretical analysis shows that AdapMen can improve the error bound and avoid compounding error under mild conditions. Experiments on the MetaDrive benchmark and Atari 2600 games validate our theoretical analysis and show that our method achieves near-expert performance with much less expert involvement and total sampling steps than previous methods. The code is available at https://github.com/liuxhym/AdapMen.

cs.LG↗

arXiv2020

Printed high-mobility p-type buffer layers on perovskite photovoltaics for efficient semi-transparent devices

Perovskite solar cells (PSCs) with transparent electrodes can be integrated with existing solar panels in tandem configurations to increase the power conversion efficiency. A critical layer in semi-transparent PSCs is the inorganic buffer layer, which protects the PSC against damage when the transparent electrode is sputtered on top. The development of n-i-p structured semi-transparent PSCs has been hampered by the lack of suitable p-type buffer layers. In this work we develop a p-type CuOx buffer layer, which can be grown uniformly over the perovskite device without damaging the perovskite or organic charge transport layers, can be grown using industrially scalable techniques and has high hole mobility (4.3 +/- 2 cm2 V-1 s-1), high transmittance (>95%), and a suitable ionisation potential for hole extraction (5.3 +/- 0.2 eV). Semi-transparent PSCs with efficiencies up to 16.7% are achieved using the CuOx buffer layer. Our work demonstrates a new approach to integrate PSCs into tandem configurations, as well as enable the development of other devices that need high quality p-type layers.

physics.app-ph↗