Robotics Summer Student Seminar (RSSS) 2022
Himanshu Gupta
Infer pedestrian's intention
Predict pedestrian's behavior given its intention
Plan a path
to its goal location
Reactive Controller
Predict and Act Controller
Issues
Issue
Need a method that determines the optimal action by reasoning over the uncertainty in pedestrian intention!
Need a method that determines the optimal action by reasoning over the uncertainty in pedestrian intention!
State
Timestep
Accurate Observations
Goal: \(a=0\) at \(s=0\)
Optimal Policy
Localize
\(a=0\)
Environment
Belief Updater
Policy
\(b\)
\(a\)
\[b_t(s) = P\left(s_t = s \mid a_1, o_1 \ldots a_{t-1}, o_{t-1}\right)\]
True State
\(s = 7\)
Observation \(o = -0.21\)
[1] Christos H. Papadimitriou and John N. Tsitsiklis. 1987. The Complexity of Markov Decision Processes. Mathematics of Operations Research 12, 3 (1987), 441–450.
Action Nodes
Belief Nodes
Roll-out Policy is important
Bai et. al, ICRA 2015
Bai et. al, ICRA 2015
Effective
Roll-out Policy is important
Bai et. al, ICRA 2015
$$\delta_s \in \{\textbf{Increase Speed, Decrease Speed,}$$ $$\textbf{Maintain Speed, Sudden Brake\}}$$
Bai et. al, ICRA 2015
ISSUES?
Bai et. al, ICRA 2015
Same as previous POMDP
Scenario 1
(Open Field)
Scenario 2 (Cafeteria Setting)
Scenario 3
(L shaped lobby)
# possible actions in POMDP Planning: 4
# possible actions in POMDP Planning: 11
# humans = 100
# humans = 200
# humans = 300
# humans = 400
Scenario 1
Evaluation Metric: Travel Time (in s)
Evaluation Metric: #Outperformed
Scenario 2
\(1D-A^*\)
\(2D-FMM\)
\(2D-PRM\)
Scenario 1
\(1D-A^*\)
\(2D-FMM\)
\(2D-PRM\)
Scenario 3
\(1D-A^*\)
\(2D-FMM\)
\(2D-PRM\)
Limited Space Planner
Extended Space Planner
Himanshu Gupta
himanshu.gupta@colroado.edu
Extended Space POMDP Planning
(AAMAS 2022)
https://github.com/himanshugupta1009/extended_space_navigation_pomdp
- Too Smooth
- Slide numbers
- Our conception of a POMDP
- If you can't fix gif, probably just remove animations
- Use same name for two-step
- Map for old approach and new approach
- In Limited Space/Extended space say (action space)
- Future work -> Next talk
- Continuous space POMDP solvers
- Results - make sure to point to which graph you are talking about
- Don't make a big deal about the non-holonomic - leave that to Will
Limited Space
Planner
Extended Space
Planners
\(1D\)-\(A^*\)
\(2D\)-\(NHV\)
Evaluation Metric: Travel Time (in s)
Evaluation Metric: #Outperformed
\(1D-A^*\)
\(2D-NHV\)