Heuristic Online Goal Recognition in Continuous Domains

Authors: Mor Vered, Gal A. Kaminka

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically evaluated our online recognition approach and the suggested heuristics over hundreds of goal recognition problems while measuring both the efficiency of the approach in terms of run-time and overall number of calls to the planner, and the performance of the approach in terms of convergence and correct ranking of the chosen goal.
Researcher Affiliation Academia Mor Vered Bar Ilan University, Ramat-Gan, Israel veredm@cs.biu.ac.il Gal A. Kaminka Bar Ilan University, Ramat-Gan, Israel galk@cs.biu.ac.il
Pseudocode Yes Algorithm 1 ONLINE GOAL RECOGNITION (R, planner)
Open Source Code No The paper does not contain any statements about making its source code publicly available, nor does it provide a link to a code repository.
Open Datasets No The paper describes generating its own observational data in a 3D navigational environment using an RRT* planner and in a simulated ROS-enabled robot environment, but it does not provide concrete access information (link, DOI, repository) for these generated datasets to be publicly available.
Dataset Splits No The paper describes generating 'goal recognition problems' and mentions the number of observed points per problem, but it does not specify explicit training, validation, or test dataset splits (e.g., percentages or sample counts).
Hardware Specification No The paper mentions using simulations (Gazebo with ROS) and existing software libraries (OMPL) for its experiments, but it does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run these simulations or computations.
Software Dependencies No The paper mentions using 'Open Motion Planning Library (OMPL [ Sucan et al., 2012])' and 'ROS [Quigley et al., 2009]' for its experiments, but it does not specify the version numbers for these software dependencies, which are required for reproducibility.
Experiment Setup Yes Each call to the planner was given a time limit of 1 sec. The cost measure being the length of the path. For the Pruning heuristic we used a threshold angle of 120 . We set 11 points spread through the cubicles environments. We then generated two observed paths from each point to all others, for a total of 110 2 goal recognition problems. and The observed robot always started at the same initial point in the middle of the field, while we experimented with 3 different starting points for the observing robot.