RoboMaster
标题: 【ICRA2019 AI Challenge Live Text Tutorial Session with Q&A】 [打印本页]
作者: training spl 时间: 2019-1-30 11:53
标题: 【ICRA2019 AI Challenge Live Text Tutorial Session with Q&A】
新闻：ICRA 人工智能挑战赛在线文本教程将于本周四举行！
北京时间（UTC+8）2019年1月31日上午10点，RoboMaster研发部的Charles Yang将为您带来直播文字直播：ICRA挑战赛准备技巧。请方便地观看本文中的实时文本并在会议期间提出问题。
如果您对如何更好地开发机器人有任何疑问，请随时在下面留下您的问题，主持人将在直播中整理这些问题并做出相应解答。
议程：
上午 10:00 - 10:10 - 对提交的团队技术提案进行一般性讨论。
上午 10:10 - 10:20 - 准备 ICRA 挑战的提示。
上午 10:20 - 11:00 - RoboMaster AI 团队实时答疑。
主持人：@Training Spl
特邀发言人：
- AI挑战赛总工程师 - Charles Yang - 论坛ID：charles.yang
- AI挑战赛工程师 - Vic Wen - 论坛ID：vvwen
- AI挑战赛工程师 - Kevin Li - 论坛ID：KevinLAD
在直播过程中，主持人和演讲嘉宾只会输入英文字母，无论用哪种语言来描述问题。
-------------------------------------------------- -------------------------------------------------- -----
直播内容：
在收到各参赛队的提案后，总结一下，我们发现大部分参赛队已经对比赛场景的机器人系统设计有了很好的掌握。但仍存在一些普遍性问题，可能对备赛工作造成负面影响：
1. 以下是您必须在游戏中实现的几个基本模块：
a) 定位
b) 运动规划和控制
c) 具有弹丸轨迹预测的视觉（装甲检测）万向伺服控制
d) 弹丸供应（从导航到视觉伺服控制）
e) 决策系统
此外，敌方机器人检测、游戏场地分割也可以应用于机器人。
2. 更加关注NAVIGATION系统的定位和避障运动规划。它是机器人的基本元件。仅知道如何运行开源包并不能保证你的机器人的性能。碰撞处罚是严厉的，没有任何让步。
3. 确保您的解决方案实用且可行，并更多地考虑工程。
For example,
a) if you use model-based filtering algorithm, please build your sensor model accurately enough or your algorithm robust enough in the game scenario, especially for UWB and IMU.
b) If you use learning based algorithm, take care of the computing source for onboard PC so that all algorithms can process in acceptable and steady frequencies at the same time.
c) If your algorithm highly depends on visual features. Think more about the light condition and possible accidents for enemy robots in the game scenario.
d) If you want to set up a wireless link for communication between robots, take the transmission quality and delay into consideration.
4. A stable system is a time-consuming work in the competition preparation period. It should take more than half of your preparation period to TEST instead of DESIGN. As the whole system is a combination of different modules, the buckets effect will have an obvious influence on the system performance, especially for visual servo control. Accurately targeting and hitting the armour of enemy robots needs to fine-tune detection, projectile trajectory prediction and gimbal servo control. In addition, decision making in the simulation is quite different from that in the real game scenario. Partially observable decision process needs testing to find the appropriate action space.
Now it is time for you to implement your solution on the real robot platform. Here is some advice about tuning the robot:
1. When you received the robot, firstly read the 《ICRA 2019 DJI RoboMaster AI Robot User Manual》. Here is the link to download it:
a) Check your circuit topology to make sure each module is connected in the right way.
b) You must know how to use the remote controller to control your robot, including chassis and gimbal motion, turning on the friction wheel and launching the projectiles under manual mode.
2. Get onboard PC ready for powering on with the proper voltage transformer and connected with MCU through a USB cable.
3. Test the robot driver on the onboard PC, make sure the robot is placed in the OPEN and SAFE area:
a) According to the tutorial, install the software dependencies, compile the robots packages and configure the udev rules on your onboard PC.
b) Stay on manual mode for remote controller, run the roborts_base_node with Rviz under ROS. Use the remote controller to control the robot, and check if you can get the correct odometry and transform topics.
c) If everything goes well, publish topics for gimbal or chassis control and switch remote controller to autonomous mode. Check if the robot moves correctly.
Here are some new information for the competition:
1. In the mid-February, we will release detailed mechanical drawings about game field including projectile supplier and protective perimeter wall. And the wall of the projectile supplier will be attached with the certain marker.
2. RoboMaster organization will not provide a standard simulator for the game this year.
3. The communication between robots through the referee system is still under development and is supposed to finish on Mid-March. So teams had better build your own wireless communication link.
4. We will be glad to hear from teams for the definition of robot illegal behaviours that would take advantage of loopholes in the rule but no more help the inspiration and development of technology. The rules will forbid such behaviours by common consent.
-----------------------------------------------------------------------------------------------------------------------------
Q&A
Q1. 关于补给站的问题：1. 能知道补给站的出弹速度吗？2. 手册里说：一分钟能接受任意一个机器人的两次补弹指令，指的是一个机器人两次，一共四次吗，还是一共两次？谢谢啦
A：1. Yes, currently the time of supply for 50 projectiles is about 3 seconds.
2. 2 times in total in 1 minute no matter how many robots get supplied.
Q2. 关于比赛规则：在比赛规则的获胜条件中有一条：“一局比赛时间耗尽时，双方机器人尚且存活，伤害高的一方获胜”。伤害高的一方获胜是指剩余血量高的一方获胜？还是命中次数多的一方获胜？伤害来源不只是射击伤害，还有其他的扣血机制。这里伤害是指（初始血量-对方剩余血量），还是只指射击命中伤害？
A：The initial value minus the remaining blood is the damage caused to the enemy.
Q3. 关于比赛规则：在淘汰赛中，上局比赛结束到下局比赛开始的时间间隔是多少？
A：After one game ends, it will jump to Five-Minute Setup Period of next game.
Q4. 关于比赛规则：补给区的触发条件？补给时长？如果由补给装置发生卡弹造成子弹补给不足如何解决？
A: After the robot sends the command to the referee system, the supply station will start replenishing.
Q5. Would mind to give some tips about when can we purchase manifold2 and referee system? And, how much are they?
A: Manifold2 will be on sales roughly in the middle of Feb. The referee system will be ready at the early March. Please pay attention to our latest announcement.
Q6. 场地周围的围栏是是什么颜色的 高反光白色？
A: In the mid-February, we will release detailed mechanical drawings about game field including projectile supplier and protective perimeter wall. And the colour of the protective perimeter will not influence the game.
Q7. 关于硬件设备：针对去年比赛时购买的UWB在最终比赛场地时，标签标号设置问题导致UWB信息不可靠问题（貌似是大家采用相同标签标号导致），今年是否还会有这个问题？
A. This is an inevitable problem unless every robot out of battlefield turns off its UWB module.
Q8. Should all the processing take place on the robot itself?
A. You can use your own computer out of the game field for computing and build a wireless link for data transmission. But the computer should be placed in the operator area.
Q9. Can we know the exact size of the Manifold2, worrying about the choice of other onboard computers?
A. Please refer to the robot size chart
Q10. When you mention "Visual Servo Control" for the Re-supply what does it mean? What is the precise mechanism that opens the small valve with 50 bullets? Being honest this doesn't look like require any kind of "vision" system.
In the mid-February, we will release detailed mechanical drawings about game field including projectile supplier and protective perimeter wall. And the wall of the projectile supplier will be attached with the certain marker.
Q11. 1. 关于模拟器的设计，我们发现实际上只需要不多的几个参数就可以描述整个游戏，比如用云台的俯仰角，底盘的角度和机器人的坐标就可以表示机器人的空间状态。所以我们打算这样来设计模拟器，就是先假设其他组的可以获得这些信息，然后我们来决策。这样简化了模拟器的设计，请问这样的设计会有什么问题吗？
2.关于强化学习的，实际比赛的时候，我们不能直接获得敌方的比赛信息，血量，枪口热度之类的，但在模拟器里训练的时候可以获得，我们想在训练网络的时候输入实际可以获得信息，但奖励函数使用这些信息，也就是网络的输入与奖励函数的参数是不一样的。这样可以吗，会有什么问题吗？提前谢谢了
1. The abstraction level of observation space and action space will definitely have an impact on the performance. And an end-to-end system is not that stable in the real world. So you may need to train the network separately for the high noise model, or just substitute high noise model with the human-designed model.
2. A new firmware that would provide enemy information for training is in our future plan, but during the competition, you are not able to know enemy information. So reward shaping may be tough work.
Q12. Is it possible to know the specific about the given IMU on the robot? Thanks
A. Development board type A： MPU6500+IST8310
Single axis gyro module: ADXRS620
Q13. "A：The initial value minus the remaining blood is the damage caused to the enemy."
Therefore, if we have one robot against two, we have double health?
A. No
Q14. 补弹指令具体指什么呢？
A. It is a protocol command sending to Referee system (from STM32 MCU to Referee system). But in the later robots version, we will provide it in the ROS sdk also. So no worry about this question.
Q15. 请问比赛中什么样的冲撞会判犯规？只要折叠围挡或者障碍么？双方机器人相互碰撞如何判罚？
A.参考规则手册3.5.3.1攻击与竞争（碰撞罚分）Q16.您好，我们购买了官方车，但是买来的机器人云台是不可控的，请问车上的云台板是完全留待自己开发的吗，还有和github上的官方队列程序是基础板的程序还是云台板的程序？非常感谢！！A. 请确保您的遥控器操作模式正确（请参阅AI Robot用户手册）。并且STM32程序是开源的（RoboRTS-Firmware：https://github.com/RoboMaster/RoboRTS-Firmware icra2019_dev分支）。板载ROS程序开源（RoboRTS： https: //github.com/RoboMaster/RoboRTS ros分支）Q17. 关于“弹丸储存器”的问题。我知道我们应该扩展它，但最大的问题是：它可以扩大多少有限制吗？我假设只要我们遵守 600x600x500 的限制就可以了？A. 只需满足裁判系统检查规范，参见规则手册附录四-赛前检查表Q18。在目前的ROS API中，我们如何控制发射动作呢？主题是什么？A. /cmd_shoot (roborts_msgs/ShootCmd)弹丸发射服务命令（包括模式、频率、数量） 参考https://robomaster.github.io/Rob ... k_docs/roborts_base（英文版几天后发布）Q19.最终50发弹丸数量如何计算？是否会根据上供弹无法完全交付弹丸仓库内全部弹丸而考虑实际装弹量？清理弹仓时，弹管内的弹丸不会被清理。
作者: 快拆小分队 时间: 2019-1-30 11:58
全英分享（我来打乱节奏）
作者: training spl 时间: 2019-1-30 14:06
怎么都没人理我，天呐
作者: Anderson Sean 时间: 2019-1-30 18:34
关于补给站的问题：1. 能知道补给站的出弹速度吗？2. 手册里说：一分钟能接受任意一个机器人的两次补弹指令，指的是一个机器人两次，一共四次吗，还是一共两次？谢谢啦
作者: Anderson Sean 时间: 2019-1-30 18:40
不好意思，这好像不是关于如何更好开发机器人的问题，可以问吗？
作者: Anderson Sean 时间: 2019-1-30 19:18
再问两个的问题哈，我是做智能决策的。1. 关于模拟器的设计，我们发现实际上只需要不多的几个参数就可以描述整个游戏，比如用云台的俯仰角，底盘的角度和机器人的坐标就可以表示机器人的空间状态。所以我们打算这样来设计模拟器，就是先假设其他组的可以获得这些信息，然后我们来决策。这样简化了模拟器的设计，请问这样的设计会有什么问题吗？2.关于强化学习的，实际比赛的时候，我们不能直接获得敌方的比赛信息，血量，枪口热度之类的，但在模拟器里训练的时候可以获得，我们想在训练网络的时候输入实际可以获得信息，但奖励函数使用这些信息，也就是网络的输入与奖励函数的参数是不一样的。这样可以吗，会有什么问题吗？提前谢谢了
作者: training spl 时间: 2019-1-31 09:43
hi, everyone
作者: training spl 时间: 2019-1-31 09:43
welcome joining to the first live session!
作者: happysf128 时间: 2019-1-31 09:45
Should we use English?
作者: Anderson Sean 时间: 2019-1-31 09:45
hi, I am watching.
作者: training spl 时间: 2019-1-31 09:46
You can use Chinese or English, but we will only answer questions in English.
作者: training spl 时间: 2019-1-31 09:47
For all participants can understand.
作者: training spl 时间: 2019-1-31 09:49
大家尽量英文提问，也支持中文提问，回答统一是英文：）
作者: happysf128 时间: 2019-1-31 09:49
What kind of questions can we ask?
作者: MissileDefence 时间: 2019-1-31 09:50
关于比赛规则：在比赛规则的获胜条件中有一条：“一局比赛时间耗尽时，双方机器人尚且存活，伤害高的一方获胜”。伤害高的一方获胜是指剩余血量高的一方获胜？还是命中次数多的一方获胜？伤害来源不只是射击伤害，还有其他的扣血机制。这里伤害是指（初始血量-对方剩余血量），还是只指射击命中伤害？
作者: MissileDefence 时间: 2019-1-31 09:51
关于比赛规则：在补给禁区判罚中：“一旦一方机器人多次进出对方补给区，或在敌方补给区持续停留时间达 5 秒以上，或有明显意图干扰敌方进行弹丸补给的行为，都会直接罚下该机器人。”其中规定了不能有明显意图的干扰敌方补弹行为。那是否可以从战术策略上选择在不进入对方补给区的情况下，增加对方进入补给区的难度呢？
作者: MissileDefence 时间: 2019-1-31 09:52
关于比赛规则：在淘汰赛中，上局比赛结束到下局比赛开始的时间间隔是多少？
作者: training spl 时间: 2019-1-31 09:52
Anything relate to AI Challenge
作者: MissileDefence 时间: 2019-1-31 09:52
关于比赛规则：补给区的触发条件？补给时长？如果由补给装置发生卡弹造成子弹补给不足如何解决？
作者: MissileDefence 时间: 2019-1-31 09:54
thank you very much !!!! 我终于说了句English ...
作者: happysf128 时间: 2019-1-31 09:54
Would mind to give some tips about when can we purchase manifold2 and referee system? And, how much are they? Thanks
作者: training spl 时间: 2019-1-31 09:55
5 mins！
作者: 还好我没放弃yl 时间: 2019-1-31 09:56
场地周围的围栏是是什么颜色的 高反光白色？
作者: training spl 时间: 2019-1-31 09:57
We will organize all the questions and answer them after the tutorial session.
作者: training spl 时间: 2019-1-31 09:57
Please stay tuned
作者: training spl 时间: 2019-1-31 09:59
10 seconds
作者: MissileDefence 时间: 2019-1-31 09:59
关于硬件设备：针对去年比赛时购买的UWB在最终比赛场地时，标签标号设置问题导致UWB信息不可靠问题（貌似是大家采用相同标签标号导致），今年是否还会有这个问题？
作者: 20133222 时间: 2019-1-31 10:00
请问补给过程如何触发补给指令？官方有没有补给结束的指示？
作者: training spl 时间: 2019-1-31 10:00
Good Morning from Shenzhen!
作者: 快拆小分队 时间: 2019-1-31 10:00
：）
作者: training spl 时间: 2019-1-31 10:00
Thanks all for joining the competition!
作者: happysf128 时间: 2019-1-31 10:01
Good afternoon from aus
作者: training spl 时间: 2019-1-31 10:01
After receiving all teams’ proposal, to sum up, we find most of the teams already had a good command of the robot system design for the game scenario. However, there are still some general problems existed that may cause negative effect on your competition preparation:
作者: training spl 时间: 2019-1-31 10:02
1. Here are few basic modules you must implement in the game:
作者: training spl 时间: 2019-1-31 10:02
a) Localization
b) Motion planning and control
c) Visual (armor detection) gimbal servo control with projectile trajectory prediction
d) Projectile supply (from navigation to visual servo control)
e) Decision making system
作者: training spl 时间: 2019-1-31 10:03
Besides, enemy robot detection, game field segmentation can also be applied to the robot.
作者: training spl 时间: 2019-1-31 10:04
2. Pay much more attention to the NAVIGATION system for localization and obstacle avoidance motion planning. It is the basic element of your robot. Only to know how to run open sourced package cannot guarantee the performance of your robot. The penalty of collision is strict without any concession.
作者: training spl 时间: 2019-1-31 10:05
3. Be sure your solution is PRACTICAL and FEASIBLE with more engineering consideration.
作者: training spl 时间: 2019-1-31 10:06
For example,
a) if you use model-based filtering algorithm, please build your sensor model accurately enough or your algorithm robust enough in the game scenario, especially for UWB and IMU.
b) If you use learning based algorithm, take care of the computing source for onboard PC so that all algorithms can process in acceptable and steady frequencies at the same time.
c) If your algorithm highly depends on visual features. Think more about the light condition and possible accidents for enemy robots in the game scenario.
d) If you want to set up a wireless link for communication between robots, take the transmission quality and delay into consideration.
作者: training spl 时间: 2019-1-31 10:08
4. A stable system is a time-consuming work in the competition preparation period. It should take more than half of your preparation period to TEST instead of DESIGN. As the whole system is a combination of different modules, the buckets effect will have an obvious influence on the system performance, especially for visual servo control. Accurately targeting and hitting the armour of enemy robots needs to fine-tune detection, projectile trajectory prediction and gimbal servo control. In addition, decision making in the simulation is quite different from that in the real game scenario. Partially observable decision process needs testing to find the appropriate action space.
作者: 木凌 时间: 2019-1-31 10:09
big lao, i'm your fensi
作者: training spl 时间: 2019-1-31 10:10
Now it is time for you to implement your solution on the real robot platform. Here is some advice about tuning the robot:
作者: training spl 时间: 2019-1-31 10:10
1. the robot, firstly read the 《ICRA 2019 DJI RoboMaster AI Robot User Manual》
作者: training spl 时间: 2019-1-31 10:11
1. When you received the robot, firstly read the 《ICRA 2019 DJI RoboMaster AI Robot User Manual》
作者: training spl 时间: 2019-1-31 10:11
here is the link to download the file: ICRA 2019 RoboMaster AI Challenge Important Documents:
https://www.robomaster.com/en-US ... ype=announcementSub
作者: training spl 时间: 2019-1-31 10:12
a) Check your circuit topology to make sure each module is connected in the right way.
b) You must know how to use the remote controller to control your robot, including chassis and gimbal motion, turning on the friction wheel and launching the projectiles under manual mode.
作者: szu_jhq 时间: 2019-1-31 10:13
lijun is really niubility
作者: Allen.Wong 时间: 2019-1-31 10:13
一颗赛艇！
作者: Xio 时间: 2019-1-31 10:14
just niubility
作者: training spl 时间: 2019-1-31 10:15
2. Get onboard PC ready for powering on with the proper voltage transformer and connected with MCU through a USB cable.
作者: suraj 时间: 2019-1-31 10:15
Should all the processing take place on the robot itself?
作者: training spl 时间: 2019-1-31 10:15
3. Test the robot driver on the onboard PC, make sure the robot is placed in the OPEN and SAFE area:
作者: training spl 时间: 2019-1-31 10:16
suraj, question received, will answer it later.
作者: 相里三石 时间: 2019-1-31 10:17
Can we know the exact size of the Manifold2, worrying about the choice of other onboard computers?
作者: training spl 时间: 2019-1-31 10:17
a) According to the tutorial, install the software dependencies, compile the robots packages and configure the udev rules on your onboard PC.
b) Stay on manual mode for remote controller, run the roborts_base_node with Rviz under ROS. Use the remote controller to control the robot, and check if you can get the correct odometry and transform topics.
c) If everything goes well, publish topics for gimbal or chassis control and switch remote controller to autonomous mode. Check if the robot moves correctly.
作者: 木凌 时间: 2019-1-31 10:17
how to win the champion ^_^
作者: training spl 时间: 2019-1-31 10:20
Here is some new information for the competition:
作者: training spl 时间: 2019-1-31 10:20
1. In the mid-February, we will release detailed mechanical drawings about game field including projectile supplier and protective perimeter wall. And the wall of the projectile supplier will be attached with the certain marker.
2. RoboMaster organization will not provide a standard simulator for the game this year.
3. The communication between robots through the referee system is still under development and is supposed to finish on Mid-March. So teams had better build your own wireless communication link.
4. We will be glad to hear from teams for the definition of robot illegal behaviours that would take advantage of loopholes in the rule but no more help the inspiration and development of technology. The rules will forbid such behaviours by common consent.
作者: training spl 时间: 2019-1-31 10:23
now we start answering questions.
作者: Stiven Ding 时间: 2019-1-31 10:23
A question realated to RoboMaster Winter Camp #LOL:
Without UWB or any other position systems like RTK, what is the best way to get the absolute position in the arena?
I am trying to do that with feedbacks from chassis encoders, which are not always expected.
作者: training spl 时间: 2019-1-31 10:23
Please send us any questions
作者: training spl 时间: 2019-1-31 10:25
问题一、关于补给站的问题：1. 能知道补给站的出弹速度吗？2. 手册里说：一分钟能接受任意一个机器人的两次补弹指令，指的是一个机器人两次，一共四次吗，还是一共两次？谢谢啦
A：1. Yes, currently the time of supply for 50 projectiles is about 3 seconds.
2. 2 times in total in 1 minute no matter how many robots get supplied.
作者: arosendo 时间: 2019-1-31 10:25
Stiven Ding, you should read about SLAM. It is possible to use a LiDAR sensor to localise yourself in the map.
I have a question: When you mention "Visual Servo Control" for the Re-supply what does it mean? What is the precise mechanism that opens the small valve with 50 bullets? Being honest this doesn't look like require any kind of "vision" system
作者: 相里三石 时间: 2019-1-31 10:26
补弹指令具体指什么呢？
作者: happysf128 时间: 2019-1-31 10:26
Is it possible to know the specific about the given IMU on the robot? Thanks
作者: training spl 时间: 2019-1-31 10:27
问题三、关于比赛规则：在比赛规则的获胜条件中有一条：“一局比赛时间耗尽时，双方机器人尚且存活，伤害高的一方获胜”。伤害高的一方获胜是指剩余血量高的一方获胜？还是命中次数多的一方获胜？伤害来源不只是射击伤害，还有其他的扣血机制。这里伤害是指（初始血量-对方剩余血量），还是只指射击命中伤害？
A：The initial value minus the remaining blood is the damage caused to the enemy.
作者: training spl 时间: 2019-1-31 10:29
问题五、关于比赛规则：在淘汰赛中，上局比赛结束到下局比赛开始的时间间隔是多少？
A：After one game ends, it will jump to Five-Minute Setup Period of next game.
作者: training spl 时间: 2019-1-31 10:30
Q6、关于比赛规则：补给区的触发条件？补给时长？如果由补给装置发生卡弹造成子弹补给不足如何解决？
A: After the robot sends the command to the referee system, the supply station will start replenishing.
作者: happysf128 时间: 2019-1-31 10:30
"A：The initial value minus the remaining blood is the damage caused to the enemy."
Therefore, if we have one robot against two, we have double health?
作者: training spl 时间: 2019-1-31 10:31
Q7\ Would mind to give some tips about when can we purchase manifold2 and referee system? And, how much are they?
A: Manifold2 will be on sales roughly in the middle of Feb. The referee system will be ready at the early March. Please pay attention to our latest announcement.
作者: arosendo 时间: 2019-1-31 10:32
Happyfs, Health1 + Health2 > Health1 + Health2. Whoever has more health wins
作者: training spl 时间: 2019-1-31 10:32
Q8. 场地周围的围栏是是什么颜色的 高反光白色？
A: In the mid-February, we will release detailed mechanical drawings about game field including projectile supplier and protective perimeter wall. And the colour of the protective perimeter will not influence the game.
作者: happysf128 时间: 2019-1-31 10:33
arosendo, I don't think that is the case. They mentioned something about intial_health - remaining_health
作者: training spl 时间: 2019-1-31 10:34
Q9、关于硬件设备：针对去年比赛时购买的UWB在最终比赛场地时，标签标号设置问题导致UWB信息不可靠问题（貌似是大家采用相同标签标号导致），今年是否还会有这个问题？
A. This is an inevitable problem unless every robot out of battlefield turns off its UWB module.
作者: training spl 时间: 2019-1-31 10:35
Q10. 请问补给过程如何触发补给指令？官方有没有补给结束的指示？
Please refer to Q6
作者: training spl 时间: 2019-1-31 10:36
Q11. Should all the processing take place on the robot itself?
A. You can use your own computer out of the game field for computing and build a wireless link for data transmission. But the computer should be placed in the operator area.
作者: training spl 时间: 2019-1-31 10:37
Q12. Can we know the exact size of the Manifold2, worrying about the choice of other onboard computers?
A. Please refer to the robot size chart
作者: 20133222 时间: 2019-1-31 10:37
请问比赛中什么样的冲撞会判犯规？只要碰到围挡或者障碍就算吗？双方机器人相互碰撞如何判罚？
作者: training spl 时间: 2019-1-31 10:38
Q13. When you mention "Visual Servo Control" for the Re-supply what does it mean? What is the precise mechanism that opens the small valve with 50 bullets? Being honest this doesn't look like require any kind of "vision" system.
In the mid-February, we will release detailed mechanical drawings about game field including projectile supplier and protective perimeter wall. And the wall of the projectile supplier will be attached with the certain marker.
作者: training spl 时间: 2019-1-31 10:39
Q2. 1. 关于模拟器的设计，我们发现实际上只需要不多的几个参数就可以描述整个游戏，比如用云台的俯仰角，底盘的角度和机器人的坐标就可以表示机器人的空间状态。所以我们打算这样来设计模拟器，就是先假设其他组的可以获得这些信息，然后我们来决策。这样简化了模拟器的设计，请问这样的设计会有什么问题吗？2.关于强化学习的，实际比赛的时候，我们不能直接获得敌方的比赛信息，血量，枪口热度之类的，但在模拟器里训练的时候可以获得，我们想在训练网络的时候输入实际可以获得信息，但奖励函数使用这些信息，也就是网络的输入与奖励函数的参数是不一样的。这样可以吗，会有什么问题吗？提前谢谢了
1. The abstraction level of observation space and action space will definitely have an impact on the performance. And an end-to-end system is not that stable in the real world. So you may need to train the network separately for the high noise model, or just substitute high noise model with the human-designed model. 2. A new firmware that would provide enemy information for training is in our future plan, but during the competition, you are not able to know enemy information. So reward shaping may be tough work.
作者: happysf128 时间: 2019-1-31 10:40
About Q13, does that means we cannot send our robot to move to a specific location to reload? Thanks
作者: training spl 时间: 2019-1-31 10:40
Q14. Is it possible to know the specific about the given IMU on the robot? Thanks
A. Development board type A： MPU6500+IST8310
Single axis gyro module: ADXRS620
作者: training spl 时间: 2019-1-31 10:41
Q15. "A：The initial value minus the remaining blood is the damage caused to the enemy."
Therefore, if we have one robot against two, we have double health?
A. No
作者: training spl 时间: 2019-1-31 10:42
Any more questions?
作者: arosendo 时间: 2019-1-31 10:42
I bought two robots but looks like they came with different programs: One of them keeps "loading and firing" bullets continuously. As we are a English-speaking team, how can I re-program the Development Board to have the same original code from the other robot?
作者: training spl 时间: 2019-1-31 10:44
Q16.补弹指令具体指什么呢？
A. It is a protocol command sending to Referee system (from STM32 MCU to Referee system). But in the later robots version, we will provide it in the ROS sdk also. So no worry about this question.
作者: 20133222 时间: 2019-1-31 10:44
请问补给站一次补给的时长是多久？有补给完成的标志吗？
作者: training spl 时间: 2019-1-31 10:45
Q18. 请问补给站一次补给的时长是多久？有补给完成的标志吗？
A. Please refer to Q1
作者: happysf128 时间: 2019-1-31 10:45
About Q14, sorry I should be more specific. Not the IMU on Development broad, but the one on the robot
Thanks
作者: training spl 时间: 2019-1-31 10:46
arosendo, we are finding a software engineer for you. one moment.
作者: happysf128 时间: 2019-1-31 10:47
Saw it, Thanks
作者: KevinLAD 时间: 2019-1-31 10:47
本帖最后由 KevinLAD 于 2019-1-31 10:49 编辑
The black cube? It is a gyro module: ADXRS620
作者: charles.yang 时间: 2019-1-31 10:48
In case the specific location is not accurate, we will add visual tag such as AprilTag. And in the mid-Feb, the specific information for the tag will be released.
作者: arosendo 时间: 2019-1-31 10:48
A question about the "Projectile reservoir". I know that we should extend it, but the big question is: Is there any limit on how much bigger can it be? I assume that as long as we respect the 600x600x500 constraints we are fine?
作者: 纵横四海3796 时间: 2019-1-31 10:48
您好，我们队伍购买了官方车，但是买来的机器人云台是不可控的，请问车上的云台板是完全留待自己开发的吗，还有和github上的官方程序是底层板的程序还是云台板的程序？thank you very much！！！
作者: 20133222 时间: 2019-1-31 10:49
请问比赛中什么样的冲撞会判犯规？只要碰到围挡或者障碍就算吗？双方机器人相互碰撞如何判罚？谢谢
作者: charles.yang 时间: 2019-1-31 10:50
Make sure your remote controller is operated in the right mode.
作者: happysf128 时间: 2019-1-31 10:51
About one robot against two, if we managed to kill one enemy robot, then there is no way the other team can beat us. Is this understanding correct? Thanks
作者: training spl 时间: 2019-1-31 10:53
Q19. 请问比赛中什么样的冲撞会判犯规？只要碰到围挡或者障碍就算吗？双方机器人相互碰撞如何判罚？
A. Refer to Rule Manual 3.5.3.1 Attack and Compete (Collision Penalty)
作者: chenrui 时间: 2019-1-31 10:54
In the current ROS API, how can we control the firing action? What is the topic for that?
| 欢迎光临 RoboMaster (https://bbs.robomaster.com/) |
Powered by Discuz! X3.2 |