 |
|
Oct 2006 - Acquired 8 Khepera II robots from K-team corp. Fall 2006 - Abhishek receives his MS degree in Mechanical Engineering Fall 2005 - Abhishek joins the RAMA Lab as a MS student and Research assistant Jan 2005 - Brian Dieckmann joins the RAMA Lab as Pratt Undergraduate Fellow Nov 2004 - Dr. Manish Kumar presented three jointly coauthored research papers at the 2004 IMECE in Anaheim, CA Nov 2004 - Dr. Manish Kumar joined the RAMA Lab as a Post doctoral Associate Oct 2004 - Dr. Garg received the Scientific Research and Leadership Award at the 2004 Heritage India Festival Sept 2004 - Dr. Garg delivered invited lectures on robotics at the Indian Institute of Technology/Roorkee and Indian Institute of Technology/ Delhi, India Aug 2004 - Ram Parimi recieved his M.S. degree in Mechanical Engineering July 2004 - Paul Nesline is the new webmaster for the RAMA LAB June 2004 - Dr. Prem Vrat, Director of Indian Institute of Technology Roorkee visits the lab June 2004 - Dr. Masayoshi Tomizuka, Director of the Dynamic Systems and Control Program at NSF visits the lab Summer 2004 - Nsi Obotetukudo from Case Western Reserve University joined the RAMA Lab for 10 weeks under the NSF/REU Program Summer 2004 - Adam Schmelzer joined the RAMA Lab as Research Assistant May 2004 - Manish Kumar received his Ph.D. degree in Mechanical Engineering May 2004 - Congratulations to Brian Schaaf and Chris Dillenbeck on their graduation with BSE degrees April 2004 - William Chandler Salinger joins the lab as an Intern for four weeks April 2004 - Ram Parami presented "Intelligent Control for Mobile Robot Navigation" in the Graduate Seminar Series |
|
Research
|
||
 |
||
| At Duke Robotics, we are not just interested in the controls of robots, but the control of multiple robots that can work together. We hope to exploit the synergetic opportunities available in many mechanical tasks. For example, two robots separately could not put a nut and a bolt assembly together on their own. But if they work with each other, they can easily accomplish this task. Also, if an object is too heavy for one robot to lift, two can do the job and the support would even be more stable. Multiple robotic control of the two ABB industrial robotic arms is sponsored by the National Science Foundation. The sensor modeling, data acquisition, data managment, and sensor fusion research is being funded by the Army Research Office and the National Science Foundation.
|
The next step for the Duke Robotics is in the direction of Artificial Intelligence. We are currently exploring ways of using neural networks and fuzzy logic to make the robots "learn" from their mistakes. The foundation of these methods is a memory capability. We envision a system of robots that no larger need to be instructed about every small move to make, but can look at past experiences and arrive at an optimum method to complete an assigned task. |
Swarm Intelligence and Control Swarm intelligence has gained considerable attention recently among the robotics research community. The attention is primarily motivated by the existence of very robust biological counterparts such as swarming in ants, flocking of birds, and schooling in fishes. The primary feature of these systems that has attracted researchers is that the intelligence associated with an individual agent (e.g. ant or bird) is very primitive, and it utilizes interactions at local level to arrive at very simple decisions. This behavior at local level emerges into a group behavior that appears to be very robust and complex. This observation in biological systems has led the interested scientists and engineers to investigate multiple agent cooperative controls problem using a bottom-up approach. We are currently developing a multiple mobile robot test bed equipped with a Cognex-5400 camera, 2 SICK LADAR sensors, and 8 Khepera mobile robots.
The mobile robots are being controlled via a radio controller through a computer. We are also working on developing formation control algorithms and strategies. The next step will be to implement these algorithms on our test-bed. Industrial Robotics Industrial Robot Coordination: Recently, research effort has been put into developing an interface between the robot controllers and Mathworks' MATLAB, a powerful PC-based engineering computation program. Simulink, a graphic building tool within MATLAB, is now being used to program the robots to perform tasks cooperatively. When the program is run, it decodes the control instructions and sends the data to the robot controllers via ethernet cable. The robots "see" what's going on around them through a mounted Cognex vision system including CCD cameras with visual recognition software. Read more. Internet Control: The control of robotic devices via the internet has become an increasingly important area of research in the last few years. We have created a web based interface for our ABB IRB 140 industrial arms that provided the user with various functionalities, such as moving the robot arms linearly to specified coordinate offsets, opening and closing the grippers, rotating the tool (gripper) about the three axes (x, y and z), accessing the F/T values, and moving the conveyer and the indexing table. Read more. Flexible Workcell Simulation: The major emphasis of this research is on machine tools and related hardware operating in flexible manufacturing work cells. Past problems and recent advances, and guidelines for work cell design were also looked at. Two flexible manufacturing work cell models were created, which are capable of manufacturing a certain part. The costs of each of the layouts were compared with the costs of manufacturing the part to determine the best layout. Read more.
Mobile Robotics Mobots: For this project, mobile robotic units with infrared sensors, temperature sensors, directional compasses, and optical cameras were built. The two robots were controlled by laptop computers mounted on top of each one. They are able to negotiate their surroundings and create a 2-D world map of their environment. Using wireless web capabilities, they can then upload the map to a global server, therefore creating a map that other mobile robots can use. The result of this is a system where each mobile robot after the first one already knows where every obstruction is in the environment. Read more. Micro-Robots: The lab is currently building two microrobots to use as research platforms in our ongoing study of multiple robot control. These robots have different locomotion systems, control systems, and sensors so that they can be used in a broad range of research applications. We are also planning to conduct comparative studies between the two robots to determine which system works best under different conditions. Read more.
Sensor Fusion Research Sensor Fusion: The research work involves formulating analytical foundation for development of formal approach to capture uncertainties involved in the sensor measurements in the form of appropriate probabilistic and analytical sensor models, and use that model to fuse data from multiple sources. The uncertainties involved in sensor measurements can arise from sensor’s limitations, change in environmental parameters, or performance of estimation/calibration algorithm (such as image processing algorithm in case of vision sensor). The research focuses on developing a unified approach to capture uncertainties arising from any possible source in the form of sensor models, and makes use of multiple vision sensors, infra-red, and sonar ranging sensors. Read more. |
|
A list of selected papers can be found on our Publications page. We hope to have abstracts and full text versions of the papers up in the near future.
|
Home Location Personnel Research Equipment Links Contact Publications |