Download presentation
Presentation is loading. Please wait.
1
Search-Based Footstep Planning
Armin Hornung, Daniel Maier, Maren Bennewitz Presentation by Dominique Gordon
2
Introduction
3
Humanoid Robots vs. Wheeled Robots
Step over obstacles Many degrees of freedom Not yet feasible to plan whole body motions in real world
4
Overview A* search algorithm wA* search algorithm
ARA* search algorithm R* search algorithm Extensions to 3D Adaptive-Level-of-Detail Planning
5
Today! First evaluation of anytime search-based footstep planning over long distances!
6
Search-Based Footstep Planning
7
Robotβs State State s = (x, y, π³) of stance foot
Footstep action a = (βx, βy, βπ³) relative to stance foot Expanding a state s - determine all successor states sβ sβs checked for collisions and discarded if invalid
8
A* Search Expands states according to f(s) = g(s) + h(s)
g(s) = actual cost of best path to current state h(s) = heuristic that estimates cost to final goal Heuristics must be ADMISSIBLE h(s) β€ the actual cost
9
A* Search with SLD as Heuristic
f(x) = = 449 f(x) = = 393 f(x) = = 447
10
A* Search Results Randomized Method
Finds optimal path Performance dependent on quality of the heuristic Slow Randomized Method Fast No guarantees on solution quality
11
Anytime Search-Based Footstep Planning
12
Weighted A* Search (wA*)
Inflates h with a factor wβ₯1 w=1 is standard A* Finds paths faster, expands fewer states Bias towards states that are closer to goal Trades quality of solution for efficiency
13
wA* Search with SLD as Heuristic, w=10
f(x) = (374) = 3815 f(x) = (253) = 2670 f(x) = (329) = 3408
14
Anytime Repairing A* (ARA*)
Series of wA* searches while reusing previous information Initially large w As time allows, search runs with lower values of w With enough time, ARA* reaches w = 1 Cost of best solution is guaranteed no worse than w times optimal solution speedup is achieved by not re-computing the state values that have been correctly computed in the previous iterations
15
Anytime Repairing A* (ARA*) explained
A* searches with decreasing w. w = 2.5 w = 1.5 w =1 The corresponding ARA* search iterations. w = 2.5 w = 1.5 w =1
16
ARA* Results Still depends on quality of heuristic
Heuristic of euclidean distance create local minima around obstacles Heuristic of 2D Dijkstra path potentially inadmissible because no stepover
17
Randomized A* Search (R*)
Depends less on quality of heuristic Series of short-range wA* searches Generates k successor states at distance β in random direction Goal states within β is added to successors as well Collision checked Finds βeasyβ local path - least number of expansions If requires too many expansions, marked AVOID Iteratively lowers w as time permits In our experiments, we used a threshold of 100 expansions to detect that a path can not be found easily
18
R* explained by me K = 4, β = 1, w = 1 (for demo purposes)
Heuristic is SLD β=1 g(S2)=5 β=1 g(S1)=7 S2 h(S2)=4 S1 S3 h(S3)=3 h(S1)=5 Goal β=1 g(S3)=5 Start h(S4)=3.5 β=1 g(S4)=3 S4 f(S1) = = 12 f(S2) = 5 +4 = 9 f(S3) = 5 +3 = 8 f(S4) = = 6.5 At every iteration, R* selects the next state s to expand from While normal A* expands s by generating all the immediate successors of state s, R* expands s by generating K states Only looks at 4 states -- so fast!
19
R* with Euclidean distance heuristic
20
ARA* vs. R* Experiments ARA* with 2D Dijkstra heuristic expands non-optimal path Inadmissible ARA* with Euclidean distance heuristic fails to find a plan in time R* with Euclidean finds good initial solutions quickly
21
Extensions to 3D 3D sensing builds elevation map
Footstep state now also has height Body of robot collision-checked against environment to execute step Non-traversable if obstacle exceeds the max step height Extended Dijkstra heuristic
23
Adaptive-Level-of-Detail Planning
24
Large open spaces with no obstacles Close to obstacles
2D path easy to compute Easy for humanoid to follow with corresponding walking controller Close to obstacles Footstep planning allows robots to step close to or over obstacles More efficient than 2D path
25
fast 2D planning in open spaces
Adaptive-Level-of-Detail planning combines fast 2D planning in open spaces with footstep planning in areas with obstacles
26
Preprocessing: Classify the environment
open area vs. close to obstacles traversable vs. non traversable obstacles
27
Execution of Adaptive-Level-of-Detail Planning
A walking controller to execute planned footsteps A velocity controller to follow the 2D path
28
Experiments with Adaptive-Level-of-Detail Planning
2D-only path = fastest computation, not optimal Global footstep plan = longest to compute, efficient path Adaptive-Level-of-Detail planning combines benefits Footstep planning only invoked where necessary Path costs 2% higher than optimal, 51% lower than 2D
29
Summary Anytime algorithms ARA* R*
3D sensing and collision checking extends footstep planning to 3D Adaptive level-of-detail planning
30
Personal Opinions Impressed by adaptive-level-of-detail planning
Great application of AI search algorithms Didnβt explain ARA* and R* algorithms well Lack of resources for algorithms
31
Questions?
32
Works Cited Search-Based Footstep Planning by Armin Hornung, Daniel Maier, Maren Bennewitz Anytime Search-Based Footstep Planning with Suboptimality Bounds by Armin Hornung, Andrew Dornbush, Maxim Likhachev, Maren Bennewitz ARA*: Anytime A* with Provable Bounds on Sub-Optimality by Maxim Likhachev, Geogg Gorgon, Sebastian Thrun R* Search by Maxim Likhachev and Anthony Stentz
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.