Differences
This shows you the differences between two versions of the page.
|
beobot_2.0_system [2013/05/05 17:17] siagian |
beobot_2.0_system [2013/12/05 15:21] (current) siagian |
||
|---|---|---|---|
| Line 12: | Line 12: | ||
| ===== Deadlines ===== | ===== Deadlines ===== | ||
| - | Past software deadlines can be found [[Beobot_2.0/Past_Software_Deadlines |here]]. | + | Past software accomplished deadlines can be found [[Beobot_2.0/Past_Software_Deadlines |here]]. |
| - | ^ ^ Todo ^ Date ^ | + | |
| - | |1. | ICRA2014: BeoRoadFinder: vision & tilted LRF | Sept 15, 2013 | | + | |
| - | |2. | IEEE AR 2013 road recognition comparison paper | Oct 31, 2013 | | + | |
| - | |3. | Implement Object search system | Dec 1, 2013 | | + | |
| - | |4. | RSS2014: Crowd navigation & understanding | Feb1, 2014 | | + | |
| - | |5. | Implement Human-Robot Interaction system | August 1, 2014 | | + | |
| + | ^ ^ Tasks ^ Date ^ | ||
| + | |1. | IEEE AR 2013 road recognition comparison paper | Dec 31, 2013 | | ||
| + | |2. | IROS 2014: BeoRoadFinder: vision & tilted LRF | Feb 1, 2014 | | ||
| + | |3. | Implement Object search system | Mar 1, 2014 | | ||
| + | |4. | RSS 2014: Crowd navigation & understanding | May 1, 2014 | | ||
| + | |5. | Implement Human-Robot Interaction system | August 1, 2014 | | ||
| - | ===== To Do ===== | ||
| - | * IEEE TRobotics 2012: Hierarchical environment representation | ||
| - | - Global Localization: lifetime learning prior, GPS integration | ||
| - | - local navigation map : BeoRoadFinder, IMU odometry | ||
| - | |||
| - | * Firmware: | ||
| - | * encoder based movements: equalize motors, take out the battery capacity variability. Trim still ok. | ||
| - | * Sensor wrapper code: isWorking() and getData() | ||
| Line 41: | Line 33: | ||
| The specific tasks that we are focusing on are: | The specific tasks that we are focusing on are: | ||
| - | * [[http://ilab.usc.edu/siagian/Research/RobotVisionLocalization/RobotVisionLocalization.html|Biologically inspired Vision Localization system]] | + | * [[http://ilab.usc.edu/siagian/Research/RobotVisionLocalization/RobotVisionLocalization.html|Biologically inspired Vision Localization system]] |
| - | * [[http://ilab.usc.edu/siagian/Research/RobotVisionNavigation/RobotVisionNavigation.html|vision navigation system]] using salient regions. [[Beobot_2.0/Software_System/GistSal_Localization_Navigation| work notes]]. | + | * [[http://ilab.usc.edu/siagian/Research/RobotVisionNavigation/RobotVisionNavigation.html|vision navigation system]] using salient regions. [[Beobot_2.0/Software_System/GistSal_Localization_Navigation| work notes]]. |
| - | * [[Beobot_2.0/Software_System/Lane_Following| road or lane following/recognition and navigation system]]. | + | * [[http://ilab.usc.edu/siagian/Research/RobotVisionNavigation/VisualRoadRecognition.html|road or lane following/recognition and navigation system]] |
| - | * recognizing people and other target objects | + | * recognizing people and other target objects |
| - | * approaching and following people and other target objects | + | * approaching and following people and other target objects |
| - | * real time human pose recognition and tracking that leads to better mobile [[Beobot_2.0/Software_System/Human_Robot_Interaction|Human Robot Interaction]] | + | * real time human pose recognition and tracking that leads to better mobile [[Beobot_2.0/Software_System/Human_Robot_Interaction|Human Robot Interaction]] |
| Line 59: | Line 51: | ||
| ==== Hierarchical Representation of the Robot's Environment ==== | ==== Hierarchical Representation of the Robot's Environment ==== | ||
| - | At the center of our software architecture is the use of hierarchical representation of the robot's environment. | + | At the center of our mobile robotic system is the use of hierarchical representation of the robot's environment. |
| We have a two level map: a global map for localization (how to recognize one's own location) and a local map for localization (how to to move about one's current environment, regardless if we know our exact location). | We have a two level map: a global map for localization (how to recognize one's own location) and a local map for localization (how to to move about one's current environment, regardless if we know our exact location). | ||
| - | The **global map** (illustrated by the left image) is a graph-based augmented topological map, which is very compact and scalable to localize large sized environments. | + | The **global map** (illustrated by the left image) is a graph-based augmented topological map, which is compact and scalable to localize large sized environments. |
| On the other hand, for navigation, we utilize an ego-centric traditional grid occupancy map as **local map** (on the right), which details the dangers in the robot's immediate surrounding. Here the robot is denoted below by a circle with an arrow indicating the robot's heading. | On the other hand, for navigation, we utilize an ego-centric traditional grid occupancy map as **local map** (on the right), which details the dangers in the robot's immediate surrounding. Here the robot is denoted below by a circle with an arrow indicating the robot's heading. | ||
| {{:globaltopologicalmap.jpg?400|}}{{:localnavigationgridmap.jpg?400|}} | {{:globaltopologicalmap.jpg?400|}}{{:localnavigationgridmap.jpg?400|}} | ||
| - | We find that it would be inefficient to use a grid map for global localization, as it is too large to maintain, but with little added information that a topological map cannot do. | + | |
| + | It would be inefficient to use a grid map for global localization, as it is too large to maintain for large scale environments, but with little added information that is not in a topological map. | ||
| We do not need to memorize every square foot of every hallway in the environment, we just need to know the one we are on. | We do not need to memorize every square foot of every hallway in the environment, we just need to know the one we are on. | ||
| By using a local map that will not be committed to the long term storage (it is robot-centric and is updated as the robot moves), we have our desired overall mobile robot representation that is both compact (for scalability) and detailed (for accuracy). | By using a local map that will not be committed to the long term storage (it is robot-centric and is updated as the robot moves), we have our desired overall mobile robot representation that is both compact (for scalability) and detailed (for accuracy). | ||
| + | ===== Navigation ===== | ||
| - | ===== Software Tools ===== | + | We use road recognition system to navigate. |
| - | The following are the firmware level software that would be useful in optimizing robot systems: | + | {{youtube>U5TFW-o7WJA?large}} |
| - | ==== Distributed Computer Communication ==== | ||
| - | The Beobot2.0 software system uses [[Beobot_2.0/Software_System/ICE| ICE]] to communicate between computers in the cluster. | ||
| - | However, we would like to improve it and add tools that can evaluate how the individual modules are performing, or whether the network is congested by which data packets. | ||
| - | **Distributed system features** that are important: | + | ===== Software Tools, Operating Systems Issues ===== |
| - | * Performance optimization tools: | + | |
| - | <code> | + | |
| - | timers on modules (evolve, updateMessage) | + | |
| - | latency information of when the packets arrive | + | |
| - | The amount of data in the **network** to if it is **congested** </code> | + | |
| - | + | ||
| - | * Packet synchronization | + | |
| - | <code> | + | |
| - | * only evoke updateMessage if a set of packets with the **same index number** is received. | + | |
| - | * Be able to set the policy for packet dropping for individual message queues</code> | + | |
| - | + | ||
| - | All comes down to serialization. | + | |
| - | + | ||
| - | + | ||
| - | ==== Operating System ==== | + | |
| - | + | ||
| - | **Real Time Robotics OS** research at the kernel level down the line. | + | |
| - | * Does not put too much priority in answering user inputs. | + | |
| - | * Knows and **Prioritize jobs** that are the most critical to the survival of the robot. | + | |
| - | * Can allocate resources properly to satisfy all the modules. | + | |
| - | + | ||
| - | MOSIX and Scyld Beowulf operating systems that encapsulates all the individual nodes that does all the job distribution internally. | + | |
| - | + | ||
| - | General notes to work your way around [[Beobot_2.0/Software_System/Mandriva| Mandriva 2009]] and [[Beobot_2.0/Software_System/Ubuntu| Ubuntu 9.10]].. | + | |
| + | The software tools related discussions can be found [[Beobot_2.0/Software_Tools| here]]. | ||
| + | It includes firmware level issues such as low level computer communication. | ||
| Back to [[index|Beobot 2.0]] | Back to [[index|Beobot 2.0]] | ||
| - | |||
| - | |||
