Surveyor Robotics Journal

Surveyor Robotics Journal

	email: support@surveyor.com SRV-1 home page Surveyor Corporation home page Subscribe to a syndicated RSS feed. Archives June 2008 May 2008 April 2008 March 2008 February 2008 January 2008 December 2007 November 2007 October 2007 September 2007 August 2007 July 2007 June 2007 May 2007 April 2007 March 2007 February 2007 January 2007 December 2006 November 2006 October 2006 September 2006 August 2006 July 2006 June 2006 May 2006 April 2006 March 2006 Februray 2006 January 2006	Tue, 27 Feb 2007 SRV-1 in Japan There was a nice mention today of the SRV-1 on robots-dreams.com as part of an article on RT Corporation, our new representative in Japan. Here's a link to the story: http://www.robots-dreams.com/2007/02/robot_fever_gro.html The founder of RT Corporation, Yuki Nakagawa, is a highly respected figure in the Japan robotics market. She is the 'Local Chair' for the RoboCup Small Size League and is the head of the RoboLDK organization , a competition that focuses on the use of robots in the home (LDK=living, dining, kitchen). She was involved in the ERATO project (Exploratory Research for Advanced Technology) as well as the National Museum of Emerging Science and Innovation and was responsible for their involvement with Honda's ASIMO. We are very grateful to Lem Fugitt of Robots Dreams for introducing us to RT Corporation and Yuki Nakagawa. Posted Tue, 27 Feb 2007 16:11 \| HTML Link \| see additional stories ... Sat, 17 Feb 2007 update for Python-based console for SRV-1 (pySRV1Console.py) We figured out two of the remaining problems with pySRV1Console: On the PC, the py2exe conversion of pySRV1Console.py to pySRV1Console.exe created serial interface issues, so you need to install Python version 2.4 or 2.5 on your PC and run pySRV1Console.py directly from Python. In any case, it is good to install Python on your PC - Python is a very cool language, and you'll need a full installation to run Pyro (Python Robotics - http://pyrorobotics.org) On the PPC Macs, there was a byte-ordering problem that caused really large timeouts between frames. Now that this is fixed, the frame rate of pySRV1Console is comparable to the Java SRV1Console performance. Here's the new download link: pySRV1Console-021707.zip (110kb) If you don't already have Python installed on your system, or if you are running a version prior to 2.4, you should download the Python installer from http://www.python.org/download/. On systems that already have Python installed, the only additional module you need to install is pySerial, which is downloaded from http://pyserial.sourceforge.net. Once you have Python installed, the console is started with: python pySRV1Console.py -com COM4 (e.g. on your PC with USB radio on COM4) or python pySRV1Console.py -com /dev/cu.SLAB_USBtoUART (e.g. on your PPC Mac) Once it's running, the main console page is accessed via your browser at: http://localhost:8888/view.html This version seems to be working quite well, but please report any issues to support@surveyor.com or post on the Surveyor Robotics Forum. Posted Sat, 17 Feb 2007 12:04 \| HTML Link \| see additional stories ... Thu, 08 Feb 2007 2007 AAAI Spring Symposium - Robots and Robot Venues: Resources for AI Education Just wanted to note that we signed on as a sponsor for the 2007 AAAI Spring Symposium on Robotics at Stanford University - March 26-28. We'll be there with a bunch of robots, so if you are planning to attend the conference, please look us up. Here are the specific details - http://www.cs.hmc.edu/roboteducation/ Posted Thu, 08 Feb 2007 18:50 \| HTML Link \| see additional stories ... "Evolutionary Robotics" and the SRV-1 It's been a month since I first posted about our exploration of adaptive / emergent behaviors for the SRV-1. In the interim, we have experimented with a variety of neural network architectures and reviewed a number of research studies. It has been an interesting journey, as we have since abandoned several of our original assumptions, e.g.: 1. that we would want create some basic neural net functions for color and feature classification that could be employed by our onboard procedural code in C or BASIC or offboard control by Python, MSRS, etc 2. that we needed to create an internal topological representation of the outside world for purpose of localization In fact, we have found that neural network architectures can be central to the operation of the robot, employing no procedural code whatsoever, instead directly connecting to processed sensor inputs and motor outputs, and that neural models can effectively model the topology of the "real world" without explicit coding of those features in structured internal representations. The most interesting and useful studies to support this revised viewpoint are found in the MIT Press publication (2000) *"Evolutionary Robotics - The Biology, Intelligence, and Technology of Self-Organizing Machines"* by Stefano Nolfi and Dario Floreano, as well as in subsequent published works by the authors. There are now numerous researchers employing this approach to robotics, as shown on The Evolutionary Robotics Homepage From a practical perspective, we are moving forward on this new path, specifically working on the task of training a soccer robot, as first described here, by defining a sequence of robot training tasks with progressively increasing complexity, e.g.: robot locates and pushes ball robot locates and pushes ball in bounded area robot locates and pushes ball in bounded area with obstacles robot locates and pushes ball toward goal in bounded area robot locates and pushes ball toward goal in bounded area with obstacles We will create, in SRV-1 firmware, an artificial neural net "brain" whose architecture can be defined by the user, with inputs supplied by core image processing routines (e.g. scan() and blob()), and outputs going direct to the motors. We plan to provide two modes of learning - supervised training, and unsupervised evolutionary self-organization. The unsupervised mode will require the use of a simulator to explore multiple generations of evolution in a reasonable timeframe, but we have a good plan for this (to be discussed in a future post). The real goal is to make the process of non-procedural robot learning accessible and understandable to any user, and this is an exciting challenge ! Posted Thu, 08 Feb 2007 13:22 \| HTML Link \| see additional stories ... Sat, 03 Feb 2007 WiFi SRV-1 update A number of SRV-1 users have been waiting on 802.11 interfaces for the robots, and things have not gone according to plan. We originally expected to have a WiFi radio module for the SRV-1 in November, but that slid to January because of firmware issues, and the latest firmware update has actually pushed things out some additional number of months, so we're now looking at alternatives. At this point, we have 4 viable WiFi module candidates: Lantronix WiPort - we tested these 802.11b/g modules back in September - see http://www.surveyor.com/cgi-bin/robot_journal.cgi/2006/09/02#047. They worked well in a hierarchical network and were easy to configure, but there were some issues: 3.3V supply, requiring additional regulator power consumption was fairly high, though we didn't fully explore the power management options external antenna only limited to 468kbps (though spec'd for 921kbps) fairly expensive if you add up the cost of the module ($120), antenna ($10), switching regulator ($10), special connector ($10) and a PCB to mount everything In its favor, we know that the WiPort works, so it remains a viable candidate. DPAC Airborne - similar in specs to the WiPort, though limited to 802.11b speeds. Interface spec is 921kbps, though this has to be tested. Likewise 3.3V, so we need another voltage regulator. Also uses external antenna. List price is $129, so cost probably works out to be comparable to the WiPort. DataHunter Mini-b - much lower cost ($79), built-in antenna option, 5V supply (no extra regulator needed), but UART spec is only 115kbps. We've contacted the manufacturer to see if the interface can be run at higher speeds. If so, this is a very attractive candidate. EZURio WISM - we haven't been able to get much hard data on these radios, but they are really small and the pictures look nice. We should have info in a few days. The goal now is to get samples of everything, and complete an evaluation within 2-3 weeks so that we can start to provide a WiFi alternative to Zigbee in March. The delays are unfortunate, but we are aware of the need, and should be able to get this back on track. Posted Sat, 03 Feb 2007 17:34 \| HTML Link \| see additional stories ...