Shichao Ou - Academia.edu (original) (raw)
Papers by Shichao Ou
Large sensor networks in applications such as surveillance and virtual classrooms, have to deal w... more Large sensor networks in applications such as surveillance and virtual classrooms, have to deal with the explosion of sensor information. Coherent presentation of data coming from such large sets of sensors becomes a problem. Thus there is a need to summarize events while retaining the spatial relationship between sensors. Also, such systems are prone to routine failures influenced by hardware, software, or the environment. To recover from such failures, fault containment can be achieved by using redundant sensors. In this paper, we define Fault Containment Unit (FCU), which has built-in alternative actions in the event of failures. However, the combinatorial explosion of alternatives in large scale sensor networks dictates that the design of FCU is hard. Our strategy is to provide an augmented virtual reality interface to a human user by projecting the current state of the system, including camera orientation and objects being tracked, onto a virtual 3D world. We present an interfa...
Proceedings of the 10th international conference on Intelligent user interfaces, 2005
Proceeding of the 5th ACM/IEEE international conference on Human-robot interaction - HRI '10, 2010
Abstract: We describe a methodology for creating new technologies for assisted living in resident... more Abstract: We describe a methodology for creating new technologies for assisted living in residential environ-ments. The number of eldercare clients is expected to grow dramatically over the next decade as the baby boom generation approaches 65 years of age. The UMass/Smith ASSIST framework aims to alleviate the strain on centralized medical providers and community services as their clientele grow, reduce the delays in service, support independent living, and therefore, improve the quality of life for the up-coming elder population. We propose a closed loop methodology wherein innovative technical systems are eld tested in assisted care facil-ities and analyzed by social scientists to create and rene residential systems for independent living. Our goal is to create technology that is embraced by clients, supports efcient delivery of support services, and facili-tates social interactions with family and friends. We introduce a series of technologies that are currently under evaluation...
In this paper we present an application solution for real-time augmented reality. We achieve almo... more In this paper we present an application solution for real-time augmented reality. We achieve almost 30 frames per second on our device and maintained good result for augmented. We use textured planar object as target. Consider of the computational complexity, we use patch feature and ZSSD template matching method for point matching. In the meantime, we maintain a database of the target template as semantics information. The semantics includes multiple key frame images of target object in different position. With this semantic database, we figure out the problems caused by viewport change and achieve robust performance.
Software tools for programming autonomous systems that are embedded in unstructured environments ... more Software tools for programming autonomous systems that are embedded in unstructured environments are increasingly important in robotics. We introduce a layered software architecture designed to facilitate the construction of hierarchical models for adaptive control programs that are learned and that can be transferred to related contexts and new robots. We focus on the interface between a robot’s sensory and motor resources and processes that learn autonomously by exploring effects of the robot’s actions. We provide an implementation of this interface called the Control Basis Application Programming Interface (CBAPI) that is designed to create hierarchical behavior and implicit knowledge out of closed-loop control primitives. The CBAPI provides a natural combinatorial means of building closed-loop controllers by combining sensory and motor resources. By so doing, it supports a variety of techniques for structuring stochastic exploration and interactive machine learning. Moreover, it...
Personal robotics is an area in which robot behavior is in service to few (or single) clients. Th... more Personal robotics is an area in which robot behavior is in service to few (or single) clients. This paper argues that the problems of human detection and recognition can be approached with simple yet efficient techniques that provide useful information to personal robots. By combining and taking advantage of coarse information such as motion, activities, shape, and color attributes, simple probabilistic inference algorithms can be applied to help a robot to become aware of nearby humans and their identities. Experimental results show that these simple models can be used to detect human presence robustly against a naturally clutterd and ambiguous background and perform well in a recognition test consisting of 10 subjects. Since this approach does not rely on the faces as crucial cue for detection or recognition, it can function under situations where conventional techniques would fail. Moreover, the simple model offers dramatic improvement in computation efficiency and can be used fo...
Robots are increasingly capable of co-existing with human beings in the places where we live and ... more Robots are increasingly capable of co-existing with human beings in the places where we live and work. I believe, however, for robots to collaborate and assist human beings in their daily lives, new methods are required for enhancing human-robot communication. In this dissertation, I focus on how a robot can acquire and refine expressive and receptive communication skills with human beings. I hypothesize that communication has its roots in motor behavior and present an approach that is unique in the following aspects: (1) representations of humans and the skills for interacting with them are learned in the same way as the robot learns to interact with other “objects,” (2) expressive behavior naturally emerges as the result of the robot discovering new utility in existing manual behavior in a social context, and (3) symmetry in communicative behavior can be exploited to bootstrap the learning of receptive behavior. Experiments have been designed to evaluate the approach: (1) as a com...
Depending upon the nonlinear feature between neural unit in artificial neural network, BP neural ... more Depending upon the nonlinear feature between neural unit in artificial neural network, BP neural network was used to develop a mathematical model for automatic testing in greenhouse environmental plantation. The design of the network structure and the learning algorithms was also discussed. Experimental statistical result of the temperature inspection model indicated that the average error was 0.4. when compared with real temperature which met the requirement of greenhouse environment. The results showed that the difficulty in adjusting the hardware was reduced when the mathematical model was adopted. It is more convenient to assemble and maintain the test system in the field.
In this paper, we propose that a robot can create a series of monitors describing its own pointin... more In this paper, we propose that a robot can create a series of monitors describing its own pointing gesture and reaching behavior and that these models can be used to infer human intention delivered by a pointing gesture and assist accordingly. This extends our previous work where we demonstrated that an intrinsically motivated robot can be designed to seek controllable relationships with the world and employ them to solicit assistance from a nearby human via expressive gestures. Preliminary experimental results demonstrate that our approach enables a robot to respond appropriately after learning a receptive quality of gesture.
The deployment of large, mobile sensor networks presents a wide range of problems, including 1) e... more The deployment of large, mobile sensor networks presents a wide range of problems, including 1) effectively communicating the important information to a user (or small set of users) without inundating him/her with irrelevant data, 2) allowing the user to affect the deployment of the network in an intuitive manner, and 3) making this interaction available to users that are located in the field. We are addressing these issues in search-and-rescue and reconnaissance domains by developing a prototype human interface architecture that includes two modes of visual interaction (panoramic imageand virtual reality-based), and speech input and output. The user interface is presented with either a desktop computer or a fully-portable, wearable computing system (Xybernaut MA IV). The latter is equipped with a threeaxis gyroscopic head tracking devicethat allows the user to employ head movements to change display perspective. The 3D virtual environment (Amstutz and Fagg, 2002) presents a coarse-...
: This paper describes the design and preliminary implementation of two distributed smart camera ... more : This paper describes the design and preliminary implementation of two distributed smart camera applications: a fall detector and an object finder. These functions are part of a novel suite of applications being developed to address aging in place health care technologies. Our approach to these applications is unique in that they are based heavily on video data, whereas other solutions may require devices that must be worn or attached to objects. The fall detector relies on features extracted from video by the camera nodes, which are sent to a central processing node where one of several machine learning techniques are applied to detect a fall. If a fall is detected, alerts are triggered both in the home and to a third party. The object finder similarly uses a boosted cascade of classifiers to visually recognize objects either by request of the user or automatically when an object is moved.
Sensors
With the steady progress of China’s agricultural modernization, the demand for agricultural machi... more With the steady progress of China’s agricultural modernization, the demand for agricultural machinery for production is widely growing. Agricultural unmanned aerial vehicles (UAVs) are becoming a new force in the field of precision agricultural aviation in China. In those agricultural areas where ground-based machinery have difficulties in executing farming operations, agricultural UAVs have shown obvious advantages. With the development of precision agricultural aviation technology, one of the inevitable trends is to realize autonomous identification of obstacles and real-time obstacle avoidance (OA) for agricultural UAVs. However, the complex farmland environment and changing obstacles both increase the complexity of OA research. The objective of this paper is to introduce the development of agricultural UAV OA technology in China. It classifies the farmland obstacles in two ways and puts forward the OA zones and related avoidance tactics, which helps to improve the safety of avia...
2007 Minneapolis, Minnesota, June 17-20, 2007, 2007
One of the most fundamental functions of the self-motion Irrigation Robot for lawn is automatic-l... more One of the most fundamental functions of the self-motion Irrigation Robot for lawn is automatic-localization in spray network proprammed in lawn, and then the automatic irrigation system are started-up to finish the irrigation operation in that network. Since the sight requirement in lawn, it is not sutable to to set elevation sticks in lawn for assistant localization. The simulation to the mankind behavious was carried out in this study. The self-adaptive fuzzy control method was used to control the robot, to make it automatic-localization in spray network proprammed in lawn.
2004, Ottawa, Canada August 1 - 4, 2004, 2004
This paper presents a novel approach in tackling the problem by introducing machine learning tech... more This paper presents a novel approach in tackling the problem by introducing machine learning technique, specifically, Reinforcement Learning (RL) and use it to search for optimal solution. An example is given in the results section to demonstrate the effectiveness of RL. We also compare performance of the Reinforcement Learning with respect to a standard planning optimization technique, Dynamic Planning. Furthermore, implications of extending this general learning framework to solve various other agricultural problems are also discussed in this paper.
In large scale surveillance applications, coherent presentation of data coming from myriad sensor... more In large scale surveillance applications, coherent presentation of data coming from myriad sensors becomes a problem. For example, tasks such as "locate an intruder" are no longer easy when the user is facing a room of monitors connected to hundreds of cameras. Therefore, there is a need for a system that allows the user to easily navigate the data space. Due to the scale of the application, such systems should also be robust with respect to hardware and software failures, as well as to varying bandwidth conditions.
Computers in Agriculture and Natural Resources, 23-25 July 2006, Orlando Florida, 2006
2005 Tampa, FL July 17-20, 2005, 2005
In the coast regions of China, strong wind activities such as typhoon are frequent. Typhoon is a ... more In the coast regions of China, strong wind activities such as typhoon are frequent. Typhoon is a major threat to greenhouses. During the typhoon periods, energy level of the winds is usually erratic, sometimes weak and sometimes strong. The naive approach of controlling greenhouse wind protection shutters according to the current wind speed will fail due to multivariate factors that affect wind speed. In this paper, we study the dynamic properties that cause the nonlinear periodic change of wind speed. A Multi-Layer Perceptron Neural Network model is designed to automatically acquire a classification model for real-time strong wind detection, using raw sensory reading of wind speed as training data. This work provides an approach for the unification of agricultural production and management control. Results show that this system is sufficient for the strong wind protection requirement of the south china coastal regions. Experiments also demonstrate that the system is robust against erratic strong wind behaviors that are frequent under real typhoon conditions.
Large sensor networks in applications such as surveillance and virtual classrooms, have to deal w... more Large sensor networks in applications such as surveillance and virtual classrooms, have to deal with the explosion of sensor information. Coherent presentation of data coming from such large sets of sensors becomes a problem. Thus there is a need to summarize events while retaining the spatial relationship between sensors. Also, such systems are prone to routine failures influenced by hardware, software, or the environment. To recover from such failures, fault containment can be achieved by using redundant sensors. In this paper, we define Fault Containment Unit (FCU), which has built-in alternative actions in the event of failures. However, the combinatorial explosion of alternatives in large scale sensor networks dictates that the design of FCU is hard. Our strategy is to provide an augmented virtual reality interface to a human user by projecting the current state of the system, including camera orientation and objects being tracked, onto a virtual 3D world. We present an interfa...
Proceedings of the 10th international conference on Intelligent user interfaces, 2005
Proceeding of the 5th ACM/IEEE international conference on Human-robot interaction - HRI '10, 2010
Abstract: We describe a methodology for creating new technologies for assisted living in resident... more Abstract: We describe a methodology for creating new technologies for assisted living in residential environ-ments. The number of eldercare clients is expected to grow dramatically over the next decade as the baby boom generation approaches 65 years of age. The UMass/Smith ASSIST framework aims to alleviate the strain on centralized medical providers and community services as their clientele grow, reduce the delays in service, support independent living, and therefore, improve the quality of life for the up-coming elder population. We propose a closed loop methodology wherein innovative technical systems are eld tested in assisted care facil-ities and analyzed by social scientists to create and rene residential systems for independent living. Our goal is to create technology that is embraced by clients, supports efcient delivery of support services, and facili-tates social interactions with family and friends. We introduce a series of technologies that are currently under evaluation...
In this paper we present an application solution for real-time augmented reality. We achieve almo... more In this paper we present an application solution for real-time augmented reality. We achieve almost 30 frames per second on our device and maintained good result for augmented. We use textured planar object as target. Consider of the computational complexity, we use patch feature and ZSSD template matching method for point matching. In the meantime, we maintain a database of the target template as semantics information. The semantics includes multiple key frame images of target object in different position. With this semantic database, we figure out the problems caused by viewport change and achieve robust performance.
Software tools for programming autonomous systems that are embedded in unstructured environments ... more Software tools for programming autonomous systems that are embedded in unstructured environments are increasingly important in robotics. We introduce a layered software architecture designed to facilitate the construction of hierarchical models for adaptive control programs that are learned and that can be transferred to related contexts and new robots. We focus on the interface between a robot’s sensory and motor resources and processes that learn autonomously by exploring effects of the robot’s actions. We provide an implementation of this interface called the Control Basis Application Programming Interface (CBAPI) that is designed to create hierarchical behavior and implicit knowledge out of closed-loop control primitives. The CBAPI provides a natural combinatorial means of building closed-loop controllers by combining sensory and motor resources. By so doing, it supports a variety of techniques for structuring stochastic exploration and interactive machine learning. Moreover, it...
Personal robotics is an area in which robot behavior is in service to few (or single) clients. Th... more Personal robotics is an area in which robot behavior is in service to few (or single) clients. This paper argues that the problems of human detection and recognition can be approached with simple yet efficient techniques that provide useful information to personal robots. By combining and taking advantage of coarse information such as motion, activities, shape, and color attributes, simple probabilistic inference algorithms can be applied to help a robot to become aware of nearby humans and their identities. Experimental results show that these simple models can be used to detect human presence robustly against a naturally clutterd and ambiguous background and perform well in a recognition test consisting of 10 subjects. Since this approach does not rely on the faces as crucial cue for detection or recognition, it can function under situations where conventional techniques would fail. Moreover, the simple model offers dramatic improvement in computation efficiency and can be used fo...
Robots are increasingly capable of co-existing with human beings in the places where we live and ... more Robots are increasingly capable of co-existing with human beings in the places where we live and work. I believe, however, for robots to collaborate and assist human beings in their daily lives, new methods are required for enhancing human-robot communication. In this dissertation, I focus on how a robot can acquire and refine expressive and receptive communication skills with human beings. I hypothesize that communication has its roots in motor behavior and present an approach that is unique in the following aspects: (1) representations of humans and the skills for interacting with them are learned in the same way as the robot learns to interact with other “objects,” (2) expressive behavior naturally emerges as the result of the robot discovering new utility in existing manual behavior in a social context, and (3) symmetry in communicative behavior can be exploited to bootstrap the learning of receptive behavior. Experiments have been designed to evaluate the approach: (1) as a com...
Depending upon the nonlinear feature between neural unit in artificial neural network, BP neural ... more Depending upon the nonlinear feature between neural unit in artificial neural network, BP neural network was used to develop a mathematical model for automatic testing in greenhouse environmental plantation. The design of the network structure and the learning algorithms was also discussed. Experimental statistical result of the temperature inspection model indicated that the average error was 0.4. when compared with real temperature which met the requirement of greenhouse environment. The results showed that the difficulty in adjusting the hardware was reduced when the mathematical model was adopted. It is more convenient to assemble and maintain the test system in the field.
In this paper, we propose that a robot can create a series of monitors describing its own pointin... more In this paper, we propose that a robot can create a series of monitors describing its own pointing gesture and reaching behavior and that these models can be used to infer human intention delivered by a pointing gesture and assist accordingly. This extends our previous work where we demonstrated that an intrinsically motivated robot can be designed to seek controllable relationships with the world and employ them to solicit assistance from a nearby human via expressive gestures. Preliminary experimental results demonstrate that our approach enables a robot to respond appropriately after learning a receptive quality of gesture.
The deployment of large, mobile sensor networks presents a wide range of problems, including 1) e... more The deployment of large, mobile sensor networks presents a wide range of problems, including 1) effectively communicating the important information to a user (or small set of users) without inundating him/her with irrelevant data, 2) allowing the user to affect the deployment of the network in an intuitive manner, and 3) making this interaction available to users that are located in the field. We are addressing these issues in search-and-rescue and reconnaissance domains by developing a prototype human interface architecture that includes two modes of visual interaction (panoramic imageand virtual reality-based), and speech input and output. The user interface is presented with either a desktop computer or a fully-portable, wearable computing system (Xybernaut MA IV). The latter is equipped with a threeaxis gyroscopic head tracking devicethat allows the user to employ head movements to change display perspective. The 3D virtual environment (Amstutz and Fagg, 2002) presents a coarse-...
: This paper describes the design and preliminary implementation of two distributed smart camera ... more : This paper describes the design and preliminary implementation of two distributed smart camera applications: a fall detector and an object finder. These functions are part of a novel suite of applications being developed to address aging in place health care technologies. Our approach to these applications is unique in that they are based heavily on video data, whereas other solutions may require devices that must be worn or attached to objects. The fall detector relies on features extracted from video by the camera nodes, which are sent to a central processing node where one of several machine learning techniques are applied to detect a fall. If a fall is detected, alerts are triggered both in the home and to a third party. The object finder similarly uses a boosted cascade of classifiers to visually recognize objects either by request of the user or automatically when an object is moved.
Sensors
With the steady progress of China’s agricultural modernization, the demand for agricultural machi... more With the steady progress of China’s agricultural modernization, the demand for agricultural machinery for production is widely growing. Agricultural unmanned aerial vehicles (UAVs) are becoming a new force in the field of precision agricultural aviation in China. In those agricultural areas where ground-based machinery have difficulties in executing farming operations, agricultural UAVs have shown obvious advantages. With the development of precision agricultural aviation technology, one of the inevitable trends is to realize autonomous identification of obstacles and real-time obstacle avoidance (OA) for agricultural UAVs. However, the complex farmland environment and changing obstacles both increase the complexity of OA research. The objective of this paper is to introduce the development of agricultural UAV OA technology in China. It classifies the farmland obstacles in two ways and puts forward the OA zones and related avoidance tactics, which helps to improve the safety of avia...
2007 Minneapolis, Minnesota, June 17-20, 2007, 2007
One of the most fundamental functions of the self-motion Irrigation Robot for lawn is automatic-l... more One of the most fundamental functions of the self-motion Irrigation Robot for lawn is automatic-localization in spray network proprammed in lawn, and then the automatic irrigation system are started-up to finish the irrigation operation in that network. Since the sight requirement in lawn, it is not sutable to to set elevation sticks in lawn for assistant localization. The simulation to the mankind behavious was carried out in this study. The self-adaptive fuzzy control method was used to control the robot, to make it automatic-localization in spray network proprammed in lawn.
2004, Ottawa, Canada August 1 - 4, 2004, 2004
This paper presents a novel approach in tackling the problem by introducing machine learning tech... more This paper presents a novel approach in tackling the problem by introducing machine learning technique, specifically, Reinforcement Learning (RL) and use it to search for optimal solution. An example is given in the results section to demonstrate the effectiveness of RL. We also compare performance of the Reinforcement Learning with respect to a standard planning optimization technique, Dynamic Planning. Furthermore, implications of extending this general learning framework to solve various other agricultural problems are also discussed in this paper.
In large scale surveillance applications, coherent presentation of data coming from myriad sensor... more In large scale surveillance applications, coherent presentation of data coming from myriad sensors becomes a problem. For example, tasks such as "locate an intruder" are no longer easy when the user is facing a room of monitors connected to hundreds of cameras. Therefore, there is a need for a system that allows the user to easily navigate the data space. Due to the scale of the application, such systems should also be robust with respect to hardware and software failures, as well as to varying bandwidth conditions.
Computers in Agriculture and Natural Resources, 23-25 July 2006, Orlando Florida, 2006
2005 Tampa, FL July 17-20, 2005, 2005
In the coast regions of China, strong wind activities such as typhoon are frequent. Typhoon is a ... more In the coast regions of China, strong wind activities such as typhoon are frequent. Typhoon is a major threat to greenhouses. During the typhoon periods, energy level of the winds is usually erratic, sometimes weak and sometimes strong. The naive approach of controlling greenhouse wind protection shutters according to the current wind speed will fail due to multivariate factors that affect wind speed. In this paper, we study the dynamic properties that cause the nonlinear periodic change of wind speed. A Multi-Layer Perceptron Neural Network model is designed to automatically acquire a classification model for real-time strong wind detection, using raw sensory reading of wind speed as training data. This work provides an approach for the unification of agricultural production and management control. Results show that this system is sufficient for the strong wind protection requirement of the south china coastal regions. Experiments also demonstrate that the system is robust against erratic strong wind behaviors that are frequent under real typhoon conditions.