Add EUDM

README.md

@@ -43,7 +43,7 @@ I regularly update [my blog in Toward Data Science](https://medium.com/@patrickl
 - [MPDM: Multipolicy decision-making in dynamic, uncertain environments for autonomous driving](https://ieeexplore.ieee.org/document/7139412) <kbd>ICRA 2015</kbd> [Behavior planning]
 - [MPDM2: Multipolicy Decision-Making for Autonomous Driving via Changepoint-based Behavior Prediction](https://www.roboticsproceedings.org/rss11/p43.pdf) <kbd>RSS 2015</kbd> [Behavior planning]
 - [MPDM3: Multipolicy decision-making for autonomous driving via changepoint-based behavior prediction: Theory and experiment](https://link.springer.com/article/10.1007/s10514-017-9619-z) <kbd>RSS 2017</kbd> [Behavior planning]
-- [EUDM: Efficient Uncertainty-aware Decision-making for Automated Driving Using Guided Branching](https://arxiv.org/abs/2003.02746) <kbd>ICRA 2020</kbd> [Wenchao Ding, Shaojie Shen, Behavior planning]
+- [EUDM: Efficient Uncertainty-aware Decision-making for Automated Driving Using Guided Branching](https://arxiv.org/abs/2003.02746) [[Notes](paper_notes/eudm.md)] <kbd>ICRA 2020</kbd> [Wenchao Ding, Shaojie Shen, Behavior planning]
 - [TPP: Tree-structured Policy Planning with Learned Behavior Models](https://arxiv.org/abs/2301.11902) <kbd>ICRA 2023</kbd> [Marco Pavone, Nvidia, Behavior planning]
 - [MARC: Multipolicy and Risk-aware Contingency Planning for Autonomous Driving](https://arxiv.org/abs/2308.12021) [[Notes](paper_notes/marc.md)] <kbd>RAL 2023</kbd> [Shaojie Shen, Behavior planning]
 - [trajdata: A Unified Interface to Multiple Human Trajectory Datasets](https://arxiv.org/abs/2307.13924) <kbd>NeurIPS 2023</kbd> [Marco Pavone, Nvidia]

paper_notes/eudm.md

@@ -0,0 +1,37 @@
+# [EUDM: Efficient Uncertainty-aware Decision-making for Automated Driving Using Guided Branching](https://arxiv.org/abs/2003.02746)
+
+_June 2024_
+
+tl;dr: A better MPDM with guided branching in both action and intention space.
+
+#### Overall impression
+In order to make POMDP more tractable it is essential to incorporate domain knowledge to efficiently make robust decisions (accelerate the problem-solving).
+
+[MPDM](mpdm.md) reduces POMDP to closed-loop evaluation (forward simulation) of a finite discrete set of semantic level policies, rather than performing evaluaton for every possible control input for every vehicle (curse of dimensionality).
+
+In EUDM, ego behavior is allowed to change, allowing more flexible decision making than MPDM. This allows EUDM can make a lane-change decision even before passing the blocking vehicle (accelerate, then lane change).
+
+EUDM couples prediction and planning module. 
+
+It is further improved by [MARC](marc.md) where it considers risk-aware contingency planning.
+
+#### Key ideas
+- DCP-Tree (domain specific closed-loop policy tree)
+	- Guided branching in action space
+	- Each trace only contains ONE change of action (more flexible than MPDM but still manageable).
+	- Each semantic action is 2s, 4 levels deep, so planning horizon of 8s.
+- CFB (conditional focused branching)
+	- conditioned on ego intention
+	- Pick out the potentially risky scenarios using **open loop** safety assement. (Open loop ignores interaction among agents, and allows checking of how serious the situation wil be if surrounding agents are completely uncoorpoerates and does not react to other agents.)
+	- select key vehicles first, only a subset of all vehicles. --> Like Tesla's AI day 2022.
+- Forward simulation
+	- IDM for longitudinal simulation
+	- PP (Pure pursuit) for lateral simulation
+- EUDM output the best policy represented by ego waypoints (0.4s apart). Then it is sent to motion planner (such as [SCC](scc.md)) for trajectory generation.
+
+#### Technical details
+- Summary of technical details, such as important training details, or bugs of previous benchmarks.
+
+#### Notes
+- What are the predictions are fed into MP alongside the BP results from EUDM?
+