[robocup-rescue-s] 2005 competition voting results

From: Cameron Skinner (cam@cs.auckland.ac.nz)
Date: Mon 10 Jan 2005 - 21:35:18 GMT


Hi everybody.

Voting for the 2005 competition rules has now been completed. Attached
is a summary of the votes.

Various parts of the simulator will be changed for the 2005 competition.
A new version of the kernel will be available no later than March 22,
beta versions will be available before then.

Changes to the 2005 are as follows:

1) The message protocol will be extended to include a "length" field.
2) Communication and perception code will be moved out of the kernel
into seperate modules.
3) Message loss will be implemented in a controlled fashion (c.f. 2004
competition where messages were lost due to UDP packets disappearing).
This will require a change from UDP to TCP communication.
4) Agents (and civilians) will suffer damage if they are near a burning
or collapsing building, not just if they are inside the building.
5) AK_MOVE will be extended to include an optional "positionExtra"
specification
6) Perception will be based on line-of-sight calculations rather than a
simple radius of vision/hearing
7) Agents will receive notification of other agent's actions that they
can observe. For example, a police force agent might see a fire brigade
extinguishing a building.
8) Aftershocks will be implemented. These may cause buildings to
collapse, possibly trapping civilians. Agents will be immune to
damage/buriedness from aftershocks.
9) The maximum number of initial burning buildings will increase to 30.
However, these buildings will be grouped into no more than 8 different
areas - i.e. there will be up to 8 initial fires, but they might begin
with several burning buildings each.
10) The space inside each building will be limited. The exact limit has
not yet been decided.
11) The kernel will not send the IDs of all objects when an agent
connects. All fixed objects (roads,nodes,buildings etc) will be sent,
but only visible moving objects (i.e. civilians) will be sent. When an
agent observes a new civilian during the simulation the appropriate
information will be sent.

The vote for whether to allow extinguishing from inside buildings was
split 50/50, so we will leave things as they are, i.e. agents can still
extinguish from inside a building.

A complete set of rules will be released in the near future.

Implementation of some of these changes is underway, including a
"librescue" module (in C++) which should hide all the communication
details such as whether we use UDP or TCP.

Volunteers for implenting any of these changes are always welcome.
Please check out the latest versions of the code via CVS from
sourceforge.net. You can check out the "development" module to get a
complete copy of the code along with a couple of tools for building a
release package.

Cameron.

-- 
Cameron Skinner
Artificial Intelligence Group
Department of Computer Science
The University of Auckland

email: cam@cs.auckland.ac.nz phone: +64 9 3737599 x82924 fax: +64 9 3737453

Post: Department of Computer Science The University of Auckland Private Bag 92019 Auckland New Zealand

1) Extending the communication protocol to include a length field for each property element. This will be easy to implement and will not affect team code aside from minor modifications to the communication layer.
12 [a] Implement for 2005
1 [b] Implement for 2006 or later
  [c] Do not implement

2) Move communication and perception code out of simulator kernel and into seperate modules. This will require a small amount of effort to implement but will not affect teams at all. The initial implementation will simply move the existing functionality into seperate modules.
11 [a] Implement for 2005
1 [b] Implement for 2006 or later
1 [c] Do not implement

Design changes
==============
3) Extend communication design to include the idea of "communication channels". This will involve a significant programming effort but will not affect teams to a large degree if option b is chosen. Option a involves defining a set of channels each with their own bandwidth and (optionally) reliability. Agents will be allowed to listen to some small number of channels (e.g. 1 or 2) and send on only one channel at a time. Centers will be able to both listen to and send to more channels than individual agents. Agents will also have an extra command available for specifying which channels they are listening and sending to. This option is closely linked to option 2 above.
  [a] Implement for 2005 with full functionality
2 [b] Implement for 2005 but only emulate existing cummunication functionality (this will not require major changes to team code)
11 [c] Implement for 2006 or later
  [d] Do not implement

4) Allow messages to be lost during communication in a controlled fashion.
8 [a] Implement for 2005
1 [b] Implement for 2006 or later
4 [c] Do not implement

5) Damage on streets. If an agent is next to a burning building or a building collapses when the agent is nearby then they may suffer damage.
10.5 [a] Implement for 2005
1.5 [b] Implement for 2006 or later
1 [c] Do not implement

6) Introduce the concept of "capabilities" for describing what different agents can do. Initially this will involve only a few capabilities (extinguish, move, clear, rescue, load etc) that emulate the existing simulator behaviour - i.e. fire agents will have both the extinguish and move capabilities, ambulances will have move, rescue and load.
2 [a] Implement for 2005 (this will require significant effort to recode the simulators and team code)
6 [b] Implement for 2006 or later
5 [c] Do not implement

7) Allow AK_MOVE to include positionExtra. This will require modification of the traffic simulator and possible minor changes to team code.
8 [a] Implement for 2005
1 [b] Implement for 2006 or later
4 [c] Do not implement

8) Seach command. This will add a SEARCH command for agents and will require the perception code to be altered. This proposal is closely linked to option 10 below and does not make sense unless 10 is also adopted.
2 [a] Implement for 2005
5.5 [b] Implement for 2006 or later
5.5 [c] Do not implement

9) Crowd behaviour. This will involve adding a new kind of object to the simulator (a crowd object) and an action for police to direct the crowd. The traffic simulator will need to be modified to allow crowds to affect the movement of vehicles.
4 [a] Implement for 2005
7 [b] Implement for 2006 or later
2 [c] Do not implement

Simulator changes
=================
10) More accurate perception model. This will change the perception to a model with the ability to reduce the range of perception dependant on factors such as smoke, buildings in the way, blocked roads etc. There are several aspects to this, so please choose one of the following options for each aspect:
2 [a] Implement for 2005
1 [b] Implement for 2006 or later
  [c] Do not implement

10.1) Line of sight calculations. This will calculate perception based on what the agents can actually see. This is computationally expensive, but line-of-sight can be calculated at start-up and cached.
6 a
4 b
10.2) Smoke. This will reduce the range of perception if an agent is inside a smoke cloud. This will also require a definition of how smoke behaves.
3 a
7 b
10.3) Probabilistic perception rather than deterministic. This will generate sensory information in a probabilistic manner - for example, if an agent is moving quickly then it might not observe some things as well as if it is stationary. This is closely related to the search command proposal (number 8, above).
1.5 a
4.5 b
4 c
10.4) Action observation. This will send updates to agents when they observe another agent taking some action, such as extinguishing a building.
9 a
1 b
10.5) Negative observations. This will send updates when you do not observe something. For example, if this agent cannot see ambulance team 4 then an update will be sent with a zero position for ambulance team 4.
5 a
5 c

11) Aftershocks. There is the potential for an aftershock to bury all rescue agents which would make it impossible to take any further actions during the run. We can either allow this or make the rescue agents immune to this kind of effect.
1 [a] Implement for 2005 with potential damage/buriedness for all agents
5 [b] Implement for 2005 with rescue agents immune to aftershock damage
2.5 [c] Implement for 2005 with ambulance agents immune to aftershock damage
2.5 [d] Implement for 2006 or later
  [e] Do not implement

1 other: Damage but not buriedness (halfway between a and b)
1 other: Between a and c

12) Causal relationships. This includes various features such as buildings collapsing due to fire, collapsing later in the simulation just because they are unstable, roads becoming blocked during the run due to building collapse, fires starting during the simulation due to collapse.
3 [a] Implement for 2005
10 [b] Implement for 2006 or later
  [c] Do not implement

Rule changes
============
13) More fires. At the moment the maximum number of initial fires is in the range [2,8]. We can increase the maximum number of starting fires to make it harder for teams to know when they have extinguished all the fires.
3 [a] Increase the maximum to a large number e.g. 50
3 [b] Increase the maximum to a slightly larger number e.g. 20
3 [c] Leave the maximum at 8
1 [d] Change the maximum to some other number

2 other: Have 8 "fire sites", but each site may be a large fire.
1 abstain

14) No extinguishing from inside buildings. Currently fire agents can execute an extinguish command from inside a neighbouring building. This rule would modify the fire simulator so that such actions are not executed. If option 16 below is adopted then this may not be necessary.
5.5 [a] Implement for 2005
1 [b] Implement for 2006 or later
6.5 [c] Do not implement

15) Burning refuges / stations. Currently refuges and stations cannot burn. The ResQ-Freiburg fire simulator allows for these buildings to be burned but this feature can be turned on or off.
4 [a] Allow refuges and stations to burn
9 [b] Do not allow refuges and stations to burn

16) Limited space in buildings. Currently any number of agents can occupy a building. Refuges and stations will still have infinite capacity. We will also have to decide how many agents can fit inside a building.
8 [a] Implement for 2005
1 [b] Implement for 2006 or later
4 [c] Do not implement

17) New agent types: water tanker and helicopter. This will require modification of the kernel and misc simulator. Water tankers will be able to transfer water to fire trucks via a new command. Helicopters will have a large perception area.
1 [a] Implement for 2005
10 [b] Implement for 2006 or later
(1 no helicoptor)
1 [c] Do not implement

1 other: Tanker b, helicoptor a

18) Do not send all IDs at startup. Currently the simulator sends the ID of every object in the world when agents connect, allowing teams to easily know when they have rescued (or at least found) all civilians. This rule would require the modification of the kernel to only send IDs when the civilians are observed. Fixed objects (nodes, roads, buildings) will still be sent as normal. Teams may need to modify their code.
8 [a] Implement for 2005
3 [b] Implement for 2006 or later
2 [c] Do not implement

19) Addition of rescue agents part way through. Currently the number and type of rescue agents is fixed at the start of the simulation. It would be possible to allow more agents to join the simulation part way through the run. This will require significant modification of the kernel and team code.
  [a] Implement for 2005
4 [b] Implement for 2006 or later
9 [c] Do not implement

20) Path planning plugin. This proposal would allow teams to provide a "path planning plugin" instead of sending move commands as a list of IDs. This proposal will be difficult to implement and will require major changes to the traffic simulator, kernel and team code.
  [a] Implement for 2005
7.5 [b] Implement for 2006 or later
5.5 [c] Do not implement

_______________________________________________
robocup-rescue-s mailing list
robocup-rescue-s@mailman.cc.gatech.edu
https://mailman.cc.gatech.edu/mailman/listinfo/robocup-rescue-s



This archive was generated by hypermail 2.1.3 : Mon 10 Jan 2005 - 22:22:50 GMT