David Claveau

Space-variant motion detection for active visual target tracking

A biologically inspired approach to active visual target tracking is presented. The approach makes use of three strategies found in biological systems: space-variant sensing, a spatio-temporal-frequency-based model of motion detection and the alignment of sensory-motor maps. Space-variant imaging is used to create a 1D array of elementary motion detectors (EMDs) that are tuned in such a way as to make it possible to detect motion over a wide range of velocities while still being able to detect motion precisely. The array is incorporated into an active visual tracking system. A method of analysis and design for such a tracking system is proposed. It makes use of a sensory-motor map which consists of a phase-plane plot of the continuous-time dynamics of the tracking system overlaid onto a map of the detection capabilities of the array of EMDs. This sensory-motor map is used to design a simple 1D tracking system and several simulations show how the method can be used to control tracking performance using such metrics as overshoot and settling time. A complete 1D active vision system is implemented and a set of simple target tracking experiments are performed to demonstrate the effectiveness of the approach.

Autonomous UAS controlled by onboard smartphone

The continued growth of unmanned aircraft systems (UAS) is driving innovation from delivery techniques to military surveillance. Cost and knowledge barriers are major limiting factors to general UAS adoption. A UAS controlled by an onboard smartphone is proposed to leverage consumer understanding and transform the emergent industry. Based upon user-supplied GPS flight path coordinates, the UAS can subsequently take flight, collect relevant data, and safely land without further instruction. This project consists of a 1.5-meter wingspan airplane carrying an Android smartphone connected via IOIO interface to servos that actuate the control surfaces and motor. With the exception of the initial GPS coordinates, no live direction is necessary for operation. Primarily, this level of autonomy was achieved by aggregating a diverse set of known algorithms to collectively validate the feasibility of smartphone-controlled autonomous systems.

A multidisciplinary design project for an introduction to engineering course

There is a great need for design projects that are suitable for freshman engineering students and that serve to introduce them to real-world engineering design work. In addition, modern engineering is increasing multidisciplinary and it is important to introduce students to this as early as possible. This paper describes a project that spans the disciplines of Industrial Engineering and Computer Science. It is a complete module that is structured on a formal engineering design process. It makes use of low-cost materials and software and attempts to give the students an enjoyable and rewarding experience. The project has been used at Arizona State University for over two years and has been well received by the students.

Progress towards a humanoid robot that learns to stand

Most of us are able to stand and likely learned to do so in the first year of our lives. While it may look easy, it is actually a difficult problem in sensory-motor control that involves multiple senses. A robot can be programmed to stand but its behavior will be more robust if it goes through an incremental learning process. Such an approach is characteristic of the emerging field of developmental or epigenetic robotics [1][2]. A mobile robot that can sense the state of its body and its environment is well suited to reinforcement learning or learning through trial and error [3]. Other types of learning based on training or imitation [4] are possible but a trial and error approach allows the robot to learn on its own and gives insight into human learning. Applying reinforcement learning to humanoid robots is challenging because their bodies have many degrees-of-freedom which leads to an enormous amout of trial and error. This paper proposes three simplifications to facilitate the application of reinforcement learning. The idea of applying reinforcement learning to robots has been explored by others [5][6]. The use of reinforcement learning in continuous spaces was addressed in [7]. Some related applications of reinforcement learning such as walking [8] and robot soccer [9] have been reported.

A Space-Variant Sensor Structure for Complex Target Detection and Tracking

Visually tracking a real-world target with an image sensor is widely applicable in robotics and human-computer interaction but is a computationally intensive task. Smart image sensors can make use of integrated motion detection circuits for target tracking, but algorithms for tracking complex, real-world targets are usually not suited to smart sensor implementations. We propose a sensor structure for tracking targets that have complex spatial frequency patterns and varying velocities. In this structure only basic motion detection circuits are used, however the distance between sensing elements is varied in order to vary the filtering properties of the system to be sensitive to a broad range of spatial frequencies and velocities. Simulation results show that it is possible to be selectively sensitive to both the different spatial frequencies of a target and to its varying velocity

A spatial variance approach to target tracking with sensor arrays

Smart sensor arrays make use of integrated motion detection circuits for target tracking. Tracking a velocity varying target is a difficult task that usually leads to a complex design and implementation. We propose an approach to target tracking that uses foveated sensor arrays that can lead to a simple design and implementation. An example system of the proposed approach is modeled and simulated. Results show improved tracking over a uniform sensor approach.

An architecture for a VLSI sensory-motor system for autonomous robots

An architecture for a VLSI sensory-motor system is presented. It makes use of ideas from behavior-based robotics and biology to achieve an obstacle avoidance behavior in an unstructured environment. Sensory-motor coordination is achieved by correlating a map of the visual field with a map which represents the robots body. Rapid decision making is facilitated by a post-receptor foveation scheme which permits the fixation of the open pathway and the localization of obstacles through spatial gradients. The foveation scheme uniquely combines space-variant processing with the possibility for high-resolution, per-pixel spatio-temporal operations across the focal plane. Only a small number of computationally simple operations are used per-pixel, potentially leading to implementations with small pixels and high fill-factors.

A Mobile Social Bar Table Based on a Retired Security Robot

The design of a social robot that serves refreshments to party guests is presented. The robot has the physical form of a bar table on wheels. It has a simple three-state behavior: if it detects drinks and refreshments on its tabletop then it wanders the room in search of people by means of a simple phonotaxis approach. If the drinks and refreshments have been removed then it returns to a designated corner of the room for reloading. The robot serves as an interesting research platform for human-robot interaction. The design is based on a retired security robot that was popular in the 1990s. Its omnidirectional synchro-drive base serves the current design well as it can easily maneuver around people. The entire design and implementation occurred over approximately two months. The design process, implementation and preliminary test results are presented.

System of 3-D Printed Components for the Rapid Prototyping of Legged Robots

A system of components designed for the rapid prototyping of different robot body plans for legged robots is described in this chapter. The components are designed and fabricated using 3-D printing technology. As such, they constitute a low-cost way to experiment with legged robots for researchers, practitioners, and students. As legged robots become more common, there will be a need for new designs and new intelligent behaviors. A system of components that facilitates experimentation can play an important role in this development. And because these components are 3-D printed, they can easily be shared and fabricated by others.

A System to Convey the Emotional Content of Text Using a Humanoid Robot

Soon we will have anthropomorphic robots that will assist us at home and at work and will be able to recite our text-based communications to us in an animated and engaging manner. This paper describes some steps taken to explore this idea with a simple humanoid robot, the NAO Aldebaran, which is capable of speech of varying pitch, speed and loudness, and has evocative color LED lights around its eyes. To convey the emotional content of text, the proposed system maps ASCII text to these capabilities. The extraction of emotion makes use of the Natural Language Toolkit (NLTK), an open-source tool for computational linguistics using Python. A two-dimensional emotion space is used to map the extracted emotion to robot action. The effectiveness of the system is explored with a simple example of emotional text and a video of the results is provided along with a time-plot of the actions.