Search papers, labs, and topics across Lattice.
This paper addresses the challenge of target interception in crowded environments by formulating the problem as a partially observable Markov decision process (POMDP) and solving it online using a tree search method. The authors compare a sequential path-speed planner with a unified planner that simultaneously optimizes steering and speed, revealing that the latter significantly outperforms the former in high-density scenarios. Specifically, at maximum crowd density, the unified planner achieves a 31 percentage point higher safe-interception rate while requiring 44% less time than the sequential approach, highlighting the limitations of traditional spatial planning methods in complex environments.
In high-density crowds, a unified steering-speed planner outperforms traditional sequential methods by a staggering 31 percentage points in safe-interception rates.
Target interception in crowded environments requires reaching a moving objective while navigating among multiple uncertain human agents. Since human navigation intent is not directly observable, the robot must reason over multiple possible future interaction outcomes. We formulate interception in crowds as a partially observable Markov decision process and solve it online using tree search under a fixed computational budget. In this setting, the action-space structure directly shapes the search tree and how computational effort is allocated. We perform a controlled comparison between a sequential path-speed planner, which first plans a spatial path and then modulates speed along it, and a unified planner that jointly branches over steering and speed within tree search. Across simulations with up to 200 humans, both approaches perform similarly at low crowd density but diverge sharply as density increases. At the highest crowd density, the sequential planner has a safe-interception rate 31 percentage points lower and requires 44% more time than the unified steering-speed planner, revealing a structural limitation of spatial restriction. Project webpage: https://tic-planning.github.io/
