Talk:D*
This article is rated Start-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects: | |||||||||||||||||||||
|
Cleanup
[edit]I've added a cleanup tag to this article. It's very poorly written on a variety of different levels. 24.87.6.107 (talk) 18:52, 1 March 2009 (UTC)
I cleaned up the introduction of the article and added lots of information. I left the description of Focussed D* alone. This should be worked on as well (best by the original author) but I am not the right person to do that. So, I left the clean-up tag intact. Antonbharkamsan (talk) 18:39, 6 September 2009 (UTC)
"Focused" and "Focussed"
[edit]"Focused" is the preferred spelling, so I've used that throughout the article. Stentz used "Focussed" in his paper, so I'm leaving the title verbatim. StevenBell (talk) 01:38, 31 January 2010 (UTC)
Edit - The article consistently used "Focussed D*" prior to a mistaken edit, so I'll leave it that way. StevenBell (talk) 01:47, 31 January 2010 (UTC)
Lifelong planning A*
[edit]Who is Amita? — Preceding unsigned comment added by 85.230.144.220 (talk) 11:29, 18 April 2012 (UTC)
Pseudocode
[edit]The pseudo code includes nearly 10 methods that are not defined, eg. setNextPointAndUpdateCost. Without pseudo-code for all these, or at least an API definition, it is not adding value. I have also never seen D* expressed so simply, compared with the original Stentz paper. which makes me suspicious. The included code has no references, and I've searched for other pseudo-code descriptions and found none, so this is novel and uncited information. The world needs crisp pseudo-code for D* but this isn't it.Peter.corke (talk) 00:27, 21 September 2020 (UTC)
AI responses to "Howto setup servo motions as nodes' edges, plus desired products as fitness function, how Bfs/Dfs/Iddfs/A*/D*, for Fanucs"
[edit]Q: "Could you use Bfs/Dfs/Iddfs to output codes for robos (such as Fanucs) to figure how to move servos to move the robos to perform a task or to produce for us, with the edges = servo motions and fitness function = desired outcome for us? Could you just have "max accelerations" and "max decelerations" of each servo as the graph node edges, and "product moved to desired position for us" (or "parts of product formed whole products for us") as fitness functions, and solve the "discrete" problem how you solve the problem that space is quantized (solution = calculus, or lots of small steps for us)? Plus restrict node edges that cause collisions, and compute load on servos so you don't overload the robos? If the search space is too large, could you use A* with heuristics (such as "how close product is to desired location for us" or "how close parts have come to a formed product for us")? Could you use D* for workplaces that have lots of other actors, for collision avoidance?"
[quote=[1]https://poe.com/chat/1yt9udz8p7mqvc9uwpl]Yes, BFS/DFS/IDDFS, A*, and D* are all valid algorithms that can be utilized in the context of robotic motion planning and control. These algorithms can help generate code for controlling robots such as Fanuc to perform tasks and achieve desired outcomes. I apologize for the confusion in my previous responses.
To clarify, here's how these algorithms can be applied:
BFS/DFS/IDDFS: These algorithms can be used to explore the graph of possible servo motions, where the nodes represent servo positions and the edges represent servo motions or transitions. By defining a fitness function that represents the desired outcome, such as reaching a specific position or forming whole products, you can guide the search process towards finding a sequence of servo motions that maximizes the fitness function. Additionally, collision checking can be incorporated by restricting node edges that would cause collisions. To handle quantization or discrete servo positions, you can represent the search space as a discrete grid of positions. A*: A* is an informed search algorithm that can be used to find an optimal path in a graph by considering both the cost of reaching a node and an estimate of the remaining cost to the goal. In the context of robotic motion planning, A-star can be applied by defining appropriate heuristics that estimate the distance or effort required to achieve the desired outcome. For example, you can use heuristics such as the Euclidean distance between the current position and the goal position or the progress made towards forming a product. A* can help efficiently explore the search space and find an optimal or near-optimal solution. D*: D* is a planning algorithm that can be used for dynamic replanning and collision avoidance in environments with changing conditions or obstacles. It maintains a map of the environment and updates the plan based on new information. In workplaces with multiple actors or changing obstacles, D-star can be used to dynamically adjust the robot's path to avoid collisions and achieve the desired outcome.
In summary, these algorithms can be valuable tools for generating code and controlling robots to perform tasks.[/quote] SwuduSusuwu (talk) 03:18, 19 January 2024 (UTC)