diff --git a/Search-based Planning/.idea/workspace.xml b/Search-based Planning/.idea/workspace.xml
index a9458b3..0342472 100644
--- a/Search-based Planning/.idea/workspace.xml
+++ b/Search-based Planning/.idea/workspace.xml
@@ -20,11 +20,11 @@
-
-
+
-
+
+
@@ -70,7 +70,7 @@
-
+
@@ -113,7 +113,7 @@
-
+
@@ -125,7 +125,7 @@
-
+
@@ -201,17 +201,17 @@
-
+
-
+
+
-
diff --git a/Search-based Planning/Search_2D/__pycache__/plotting.cpython-37.pyc b/Search-based Planning/Search_2D/__pycache__/plotting.cpython-37.pyc
index 8a911c1..8bc3bac 100644
Binary files a/Search-based Planning/Search_2D/__pycache__/plotting.cpython-37.pyc and b/Search-based Planning/Search_2D/__pycache__/plotting.cpython-37.pyc differ
diff --git a/Search-based Planning/Search_2D/a_star.py b/Search-based Planning/Search_2D/a_star.py
index f56a2d2..fa5e2bd 100644
--- a/Search-based Planning/Search_2D/a_star.py
+++ b/Search-based Planning/Search_2D/a_star.py
@@ -117,9 +117,9 @@ class Astar:
def main():
x_start = (5, 5) # Starting node
- x_goal = (49, 5) # Goal node
+ x_goal = (49, 25) # Goal node
- astar = Astar(x_start, x_goal, 1, "manhattan")
+ astar = Astar(x_start, x_goal, 1, "euclidean")
plot = plotting.Plotting(x_start, x_goal) # class Plotting
fig_name = "A* Algorithm"
diff --git a/Search-based Planning/Search_2D/bidirectional_a_star.py b/Search-based Planning/Search_2D/bidirectional_a_star.py
new file mode 100644
index 0000000..41f7f89
--- /dev/null
+++ b/Search-based Planning/Search_2D/bidirectional_a_star.py
@@ -0,0 +1,149 @@
+"""
+Bidirectional_a_star 2D
+@author: huiming zhou
+"""
+
+import os
+import sys
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)) +
+ "/../../Search-based Planning/")
+
+from Search_2D import queue
+from Search_2D import plotting
+from Search_2D import env
+
+
+class BidirectionalAstar:
+ def __init__(self, x_start, x_goal, heuristic_type):
+ self.xI, self.xG = x_start, x_goal
+ self.heuristic_type = heuristic_type
+
+ self.Env = env.Env() # class Env
+
+ self.u_set = self.Env.motions # feasible input set
+ self.obs = self.Env.obs # position of obstacles
+
+ self.g_fore = {self.xI: 0, self.xG: float("inf")}
+ self.g_back = {self.xG: 0, self.xI: float("inf")}
+
+ self.OPEN_fore = queue.QueuePrior()
+ self.OPEN_fore.put(self.xI, self.g_fore[self.xI] + self.h(self.xI, self.xG))
+ self.OPEN_back = queue.QueuePrior()
+ self.OPEN_back.put(self.xG, self.g_back[self.xG] + self.h(self.xG, self.xI))
+
+ self.CLOSED_fore = []
+ self.CLOSED_back = []
+
+ self.Parent_fore = {self.xI: self.xI}
+ self.Parent_back = {self.xG: self.xG}
+
+ def searching(self):
+ visited_fore, visited_back = [], []
+ s_meet = self.xI
+
+ while not self.OPEN_fore.empty() and not self.OPEN_back.empty():
+
+ # solve foreward-search
+ s_fore = self.OPEN_fore.get()
+ if s_fore in self.Parent_back:
+ s_meet = s_fore
+ break
+ visited_fore.append(s_fore)
+ for u in self.u_set:
+ s_next = tuple([s_fore[i] + u[i] for i in range(len(s_fore))])
+ if s_next not in self.obs:
+ new_cost = self.g_fore[s_fore] + self.get_cost(s_fore, u)
+ if s_next not in self.g_fore:
+ self.g_fore[s_next] = float("inf")
+ if new_cost < self.g_fore[s_next]:
+ self.g_fore[s_next] = new_cost
+ self.Parent_fore[s_next] = s_fore
+ self.OPEN_fore.put(s_next, new_cost + self.h(s_next, self.xG))
+
+ # solve backward-search
+ s_back = self.OPEN_back.get()
+ if s_back in self.Parent_fore:
+ s_meet = s_back
+ break
+ visited_back.append(s_back)
+ for u in self.u_set:
+ s_next = tuple([s_back[i] + u[i] for i in range(len(s_back))])
+ if s_next not in self.obs:
+ new_cost = self.g_back[s_back] + self.get_cost(s_back, u)
+ if s_next not in self.g_back:
+ self.g_back[s_next] = float("inf")
+ if new_cost < self.g_back[s_next]:
+ self.g_back[s_next] = new_cost
+ self.Parent_back[s_next] = s_back
+ self.OPEN_back.put(s_next, new_cost + self.h(s_next, self.xI))
+
+ return self.extract_path(s_meet), visited_fore, visited_back
+
+ def extract_path(self, s):
+ path_back_fore = [s]
+ s_current = s
+
+ while True:
+ s_current = self.Parent_fore[s_current]
+ path_back_fore.append(s_current)
+
+ if s_current == self.xI:
+ break
+
+ path_back_back = []
+ s_current = s
+
+ while True:
+ s_current = self.Parent_back[s_current]
+ path_back_back.append(s_current)
+
+ if s_current == self.xG:
+ break
+
+ return list(reversed(path_back_fore)) + list(path_back_back)
+
+ def h(self, state, goal):
+ """
+ Calculate heuristic.
+ :param state: current node (state)
+ :param goal: goal node (state)
+ :return: heuristic
+ """
+
+ heuristic_type = self.heuristic_type
+
+ if heuristic_type == "manhattan":
+ return abs(goal[0] - state[0]) + abs(goal[1] - state[1])
+ elif heuristic_type == "euclidean":
+ return ((goal[0] - state[0]) ** 2 + (goal[1] - state[1]) ** 2) ** (1 / 2)
+ else:
+ print("Please choose right heuristic type!")
+
+ @staticmethod
+ def get_cost(x, u):
+ """
+ Calculate cost for this motion
+ :param x: current node
+ :param u: input
+ :return: cost for this motion
+ :note: cost function could be more complicate!
+ """
+
+ return 1
+
+
+def main():
+ x_start = (5, 5) # Starting node
+ x_goal = (49, 25) # Goal node
+
+ bastar = BidirectionalAstar(x_start, x_goal, "euclidean")
+ plot = plotting.Plotting(x_start, x_goal) # class Plotting
+
+ fig_name = "Bidirectional-A* Algorithm"
+ path, v_fore, v_back = bastar.searching()
+ plot.animation_bi_astar(path, v_fore, v_back, fig_name) # animation generate
+
+
+if __name__ == '__main__':
+ main()
diff --git a/Search-based Planning/Search_2D/plotting.py b/Search-based Planning/Search_2D/plotting.py
index f021782..a8ec8b2 100644
--- a/Search-based Planning/Search_2D/plotting.py
+++ b/Search-based Planning/Search_2D/plotting.py
@@ -89,6 +89,35 @@ class Plotting:
plt.show()
+ def animation_bi_astar(self, path, v_fore, v_back, name):
+ self.plot_grid(name)
+ self.plot_visited_bi(v_fore, v_back)
+ self.plot_path(path)
+ plt.show()
+
+ def plot_visited_bi(self, v_fore, v_back):
+ if self.xI in v_fore:
+ v_fore.remove(self.xI)
+
+ if self.xG in v_back:
+ v_back.remove(self.xG)
+
+ len_fore, len_back = len(v_fore), len(v_back)
+
+ for k in range(max(len_fore, len_back)):
+ if k < len_fore:
+ plt.plot(v_fore[k][0], v_fore[k][1], linewidth='3', color='gray', marker='o')
+ if k < len_back:
+ plt.plot(v_back[k][0], v_back[k][1], linewidth='3', color='cornflowerblue', marker='o')
+
+ plt.gcf().canvas.mpl_connect('key_release_event',
+ lambda event: [exit(0) if event.key == 'escape' else None])
+
+ if k % 10 == 0:
+ plt.pause(0.001)
+ plt.pause(0.01)
+
+
@staticmethod
def color_list():
cl_v = ['silver', 'wheat', 'lightskyblue', 'plum', 'slategray']
diff --git a/Search-based Planning/gif/Astar.gif b/Search-based Planning/gif/Astar.gif
index 786bd9d..0cc0254 100644
Binary files a/Search-based Planning/gif/Astar.gif and b/Search-based Planning/gif/Astar.gif differ
diff --git a/Search-based Planning/gif/Bi-Astar.gif b/Search-based Planning/gif/Bi-Astar.gif
new file mode 100644
index 0000000..4e4301a
Binary files /dev/null and b/Search-based Planning/gif/Bi-Astar.gif differ