ASEN 6519 - DMU ++ Paper Presentation on "PAWS"
Himanshu Gupta
Date - 18 September 2023
Fang et al. (AAMAS 2017)
MOTIVATION
- Poaching is the illegal hunting or capturing of wild animals, usually associated with land use rights
- Poaching can lead to disastrous consequences
- Population loss
- Unbalanced Ecosystem
- Spread of major illnesses
MOTIVATION
- So, how can we prevent/reduce poaching?
- Patroling is the most common and effective preventive measure at the moment.
- But figuring out the best patrolling routes to minimize poaching over a large-scale conservation area is difficult.
- Limited patroling resources
- Can AI help?
MOTIVATION
- PAWS-Initial (Yang et al. 2014) used a game theoretic formulation to solve this problem.
- Protection Assistant for Wildlife Security
- Why the game theoretic approach?
- Has 4 major limitations
- So, now what?
CONTRIBUTION
- Developed PAWS, a more realistic and practical game-theoretic application deployed in Southeast Asia for optimizing foot patrols to combat poaching.
- Addressed major limitations of its predecessor, PAWS-Initial.
- PAWS is a regularly deployed application, while PAWS-Initial was a proposed decision aid.
- PAWS is a regularly deployed application, while PAWS-Initial was a proposed decision aid.
- Patrollers and patrol planners agreed that PAWS generates detailed suggested routes that can guide the actual patrol.
- Feedback: Suggested routes were easier to follow, compared with the routes from PAWS-Initial.
- Reduces/Removes the mental effort of planning routes.
Theory
- Stackelberg game: One player (the "leader") moves first, and other players ("the followers") observe their move and move after them.
Theory
- Stackelberg game: One player (the "leader") moves first, and other players ("the followers") observe their move and move after them.
Theory
- Stackelberg game: One player (the "leader") moves first, and other players ("the followers") observe their move and move after them.
Theory
- Minimax regret game - a game where the best strategy is the one that minimizes the maximum regret. Essentially, this is the technique for a 'sore loser' who does not wish to make the wrong decision.
Payoff Table
Regret
PAWS-Initial
- Solves a Stackelberg security game (SSG)
- Discretize conservation area into a grid.
- \(U^a_{p,i},U^a_{r,i},U^d_{p,i},U^d_{r,i} \)
- Defender strategy can be represented using a coverage vector \(c\).
- \(<c_i>\) - probability defender goes to target i
- \(<c_i>\) - probability defender goes to target i
- Given a defender strategy \(c\) and the penalty and reward values, the players’ expected utilities \(U^a_i\) and \(U^d_i\) when target i is attacked can be calculated.
PAWS-Initial LIMITATIONS
- Ignored topographic information
PAWS-Initial LIMITATIONS
- Ignored topographic information (go through a lake)
PAWS-Initial LIMITATIONS
- Ignored topographic information (too much gradient)
PAWS-Initial LIMITATIONS
- Ignored topographic information
- Assumes payoff values of the targets, \(U^a_{r,i}\) are known and fixed
- Animals can migrate from season to season or depending on food availability.
- Animals can migrate from season to season or depending on food availability.
- Doesn't scale to large areas.
- Finer discretization is needed but that makes the problem exponential.
- Finer discretization is needed but that makes the problem exponential.
PAWS-Initial LIMITATIONS
4. Considers covering individual grid cells, but not feasible paths.
So, solution?
PAWS!
Approach
Input and Initial Analysis
- Produce a posterior predictive for animals using a Bayesian framework.
- MaxEnt for human activity distribution
- using geographical data, e.g., distance to water, slope, elevation.
Building Game Model
- Based on the input information and the estimated distribution, build a game model
- Use SSG to abstract the strategic interaction between the patroller and the poacher.
- Use SSG to abstract the strategic interaction between the patroller and the poacher.
- Building a game model involves
- defender action modeling
- adversary action modeling
- payoff modeling.
Building Game Model
- Defender Action Modeling
- Patroller's feedback - detailed guidance is needed!
- If they use a fine-grained grid where every grid cell is a target, computing the optimal patrolling strategy is computationally challenging (PROBLEM)
- Hierarchical modeling approach (SOLUTION)
- allows to attain a good compromise between scaling up and providing detailed guidance
- (1km x 1km Grid cells and 50m x 50m Raster pieces)
- Defender actions are patrol routes defined over a virtual “street map”
- Patroller's feedback - detailed guidance is needed!
Building Game Model
- Defender Action Modeling (Hierarchical modeling approach)
- Generate a street map
- A graph consisting of nodes and edges, where the set of nodes is a small subset of the raster pieces and edges are sequences of raster pieces linking the nodes.
- Nodes are Key Access Points (KAPs) and edges as route segments.
- Generate a street map
Building Game Model
- Defender Action Modeling:
- Building a street map (3 steps)
- Step 1: determine the accessibility type for each raster piece
- Step 2: define KAPs
- Step 3: find route segments to link the KAPs.
Poacher Action Modeling
- To ensure scalability, poacher’s actions are defined over the coarse grid cells.
- In this game, the assumption is that the poacher can observe the defender’s mixed strategy and then choose a grid cell to attack.
- Poacher is assumed to be boundedly rational, and their actions can be described by the SUQR model.
- A weighted combination of coverage probability, the poacher's reward and the poacher's penalty
Payoff Modeling
- Models a zero-sum game
- reward for attacker = penalty for defender
- reward for attacker = penalty for defender
- Attacker's reward at a target (grid cell) is decided by the animal distribution.
- However, animal density is difficult to determine exactly and can vary due to seasonal or dynamic migration.
- This makes the payoff uncertain.
- Need to handle uncertainty in the players’ payoff values.
- Use intervals to represent payoff uncertainty in PAWS.
- If the patrollers patrol a cell more frequently, there is less uncertainty in the poacher’s payoffs at that target and thus a smaller size of the payoff intervals.
Calculate Patrol Strategy
- The algorithm should
- Generate patrol routes over the street map over the entire conservation area region
- Address payoff uncertainty
- Work with bounded rationality of the adversary (SUQR)
- instead of assuming a completely rational agent.
- Generate patrol routes over the street map over the entire conservation area region
ARROW
(Nguyen et al. 2015)
Calculate Patrol Strategy
- Solution: ARROW with BLADE
- ARROW finds the strategy that minimizes regret for the patrollers over the coarse grid cells.
- BLADE makes it scalable
- ARROW finds the strategy that minimizes regret for the patrollers over the coarse grid cells.
Constraint: \( c_1 \geq (c_2 + c_3 + c_4) \)
Calculate Patrol Strategy
Calculate Patrol Strategy
- PAWS calculates the patrol strategy consisting of a set of patrol routes and the corresponding probability for taking them.
Trading Off Exploration and Exploitation
- PAWS-EvE
- Offers the option of assigning a probability range for selecting an explorative route.
- Explorative routes cover a significant portion of previously unpatrolled land while Exploitative routes cover a significant portion of land previously patrolled.
- Exploitative routes are great, but since the objective of PAWS is to minimize poaching activity, it is necessary to also take explorative routes.
- Offers the option of assigning a probability range for selecting an explorative route.
Deployment and Evaluation
- PAWS patrols are now regularly deployed at a conservation area in Malaysia.
- Daily patrols from base camps.
- 10 km per day distance limit.
- Impossible to consider each raster piece as a separate target or consider all possible routes over the raster pieces.
- Hierarchical approach: 8.57(= 194.33/22.67) KAPs and 80 route segments in each grid cell on average
Deployment and Evaluation
- PAWS patrol lasts for 4-5 days and is executed by a team of 3-7 patrollers.
- During the patrol, they detect animal and human activity signs and record them with detailed comments and photos.
- After the patrol, the data manager will put all the information into a database, which helps refine the map and information for future implementations of PAWS.
Deployment and Evaluation
Deployment and Evaluation
Deployment and Evaluation
PAWS-Initial
PAWS
Critique and Limitations
- Motivation for why the game theoretic approach is the best way to solve this problem?
- Why is the minimax regret game formulation better than SSG?
- Different discretization for poacher and patroller
- The paper has almost no math in it. How does ARROW find the patrol strategy?
- Maybe that is also good?
- Maybe that is also good?
- No qualitative results that show PAWS works better than PAWS-Initial.
- Same for PAWS-EvE
Impact and Legacy
- The paper came out in 2017 and has 68 citations.
- PAWS-Initial came out in 2014 and has 235 citations.
- PAWS-Initial came out in 2014 and has 235 citations.
- A fascinating real-life application for game theoretic approaches.
- Opened the path for other security related real-life applications, like patroling of large warehouses or college campuses.
Future Work
- They didn't mention any in their paper.
- Other than expanding it to other large conservation areas in other countries.
- Other than expanding it to other large conservation areas in other countries.
- Can be formulated using the Dec-POMDP framework.
- Comparing the two approaches to see which works better is a good research question we don't know the answer to.
- We have a paper on Dec-POMDPs towards the end of the class.
CONTRIBUTION
- Developed PAWS, a more realistic and practical game-theoretic application deployed in Southeast Asia for optimizing foot patrols to combat poaching.
- Addressed major limitations of its predecessor, PAWS-Initial.
- PAWS is a regularly deployed application, while PAWS-Initial was a proposed decision aid.
- PAWS is a regularly deployed application, while PAWS-Initial was a proposed decision aid.
- Patrollers and patrol planners agreed that PAWS generates detailed suggested routes that can guide the actual patrol.
- Suggested routes were easier to follow, compared with the routes from PAWS-Initial.
- PAWS was able to guide them towards poaching hotspots.
- Reduces/Removes the mental effort of planning routes.
ASEN 6519 - DMU ++ Paper Presentation PAWS
By Himanshu Gupta
ASEN 6519 - DMU ++ Paper Presentation PAWS
- 64