IntentionAware Navigation in Crowds with ExtendedSpace POMDP Planning
Himanshu Gupta
Bradley Hayes
Zachary Sunberg
Autonomous systems in the real world
A capable robot must
Infer pedestrian's intention
Predict pedestrian's behavior given its intention
Plan a path
to its goal location
Prior Work
Reactive Controller
Predict and Act Controller
Issues
 Pedestrian Model?
 Future effect of immediate actions?
Issue
 Uncertainty in pedestrian intention estimation?
Need a method that determines the optimal action for the vehicle at any given time by reasoning over the uncertainty in pedestrian intention estimation?
Need a method that determines the optimal action for the vehicle at any given time by reasoning over the uncertainty in pedestrian intention estimation?
Twostep Approach
Bai et. al, ICRA 2015
Twostep Approach
Bai et. al, ICRA 2015
Solving POMDP using DESPOT
 STATE:
\((x_c,y_c,\theta_c,v_c, g_c)\)
corresponding to the 2D pose, speed and goal of the vehicle.
\((x_i,y_i,v_i, g_i)\)
corresponding to the \(i^{th}\) pedestrian's state
 ACTION:
$$\delta_s \in \{\textbf{Increase Speed, Decrease Speed,}$$ $$\textbf{Maintain Speed, Sudden Brake\}}$$
Effective
Rollout Policy is important
Bai et. al, ICRA 2015
Twostep Approach
$$\delta_s \in \{\textbf{Increase Speed, Decrease Speed,}$$ $$\textbf{Maintain Speed, Sudden Brake\}}$$
Bai et. al, ICRA 2015
\(\textbf{1DA}^*\) Approach
ISSUES?
 Decoupling of heading angle planning and speed planning often leads to unnecessary stalling of the vehicle!
 Hybrid A* path can't be found at at every time step!
Bai et. al, ICRA 2015
2D Approach
2D Approach
Solving POMDP using DESPOT
 STATE:
\((x_c,y_c,\theta_c,v_c, g_c)\)
corresponding to the 2D pose, speed and goal of the vehicle.
\((x_i,y_i,v_i, g_i)\)
corresponding to the \(i^{th}\) pedestrian's state
 ACTION:
$$\delta_s(t) \in \{\textbf{Increase Speed, Decrease Speed,}$$ $$\textbf{Maintain Speed, Sudden Brake\}}$$
Same as previous POMDP
 ACTION:
$$\mathcal{a = ( \delta_\theta , \delta_s )}$$
2D Approach
 Critical Challenge: Determining a good rollout policy for the vastly increased set of states reachable in the tree search.
Effective rollout policy
 Obtain a path using multi query motion planning technique
 Probabilistic RoadMap (PRM)
 Fast Marching Method (FMM)
 Rollout policy: Execute a reactive controller over the obtained path
Probabilistic RoadMaps (PRM) for MultiQuery Path Planning
Simulation Environment
 Environment: \(100\)m x \(100\)m square field

Autonomous vehicle: A holonomic vehicle.
 Inspired by Kinova MOVO
 Max speed: \(2\) m/s
Experimental Scenarios
Scenario 1
(Open Field)
Scenario 2 (Cafeteria Setting)
Scenario 3
(L shaped lobby)
Planners
# possible actions in POMDP Planning: 4
# possible actions in POMDP Planning: 11
Experimental Details
 For each scenario, we ran sets of 100 different experiments with different pedestrian densities in the environment.
# humans = 100
# humans = 200
# humans = 300
# humans = 400
Scenario 1
Results
Evaluation Metric: Travel Time (in s)
Results
Evaluation Metric: #Outperformed
Scenario 2
\(1DA^*\)
\(2DFMM\)
\(2DPRM\)
Results
Limited Space Planner
Extended Space Planner
Conclusion
Thank You!
Himanshu Gupta
himanshu.gupta@colroado.edu
Extended Space POMDP Planning
(AAMAS 2022)
https://github.com/himanshugupta1009/extended_space_navigation_pomdp
Summary

We proposed a new technique for navigation problems with arbitrary state uncertainty by incorporating multiquery path planning techniques for effective tree search using online solvers for a POMDP
 Probabilistic RoadMaps

Fast Marching Methods
 We demonstrated that our technique outperforms the current stateoftheart method significantly in terms of travel time while being just as safe!
Experimental Details
 In simulations, the planning time for the vehicle at each step is 0.5 seconds
Experiments (NHV)
Limited Space
Planner
Extended Space
Planners
\(1D\)\(A^*\)
\(2D\)\(NHV\)
Results (NHV)
Evaluation Metric: Travel Time (in s)
Evaluation Metric: #Outperformed
Results (NHV)
\(1DA^*\)
\(2DNHV\)
Results (NHV)
AAMAS Conference Presentation
By Himanshu Gupta
AAMAS Conference Presentation
 278