Hanlan's paper

Author: zkingston

_bibliography/papers.bib

@@ -6,10 +6,23 @@ @string{iros
 @string{ral = {IEEE Robotics and Automation Letters}}
 @string{tro = {IEEE Transactions on Robotics}}
 @string{ijrr = {The International Journal of Robotics Research}}
+@misc{yang2025pachs,
+  title        = {Parallel Heuristic Search as Inference for Actor-Critic Reinforcement Learning Models},
+  author       = {Hanlan Yang and Itamar Mishani and Luca Pivetti and Zachary Kingston and Maxim Likhachev},
+  abstract     = {Actor-Critic models are a class of model-free deep reinforcement learning (RL) algorithms that have demonstrated effectiveness across various robot learning tasks. While considerable research has focused on improving training stability and data sampling efficiency, most deployment strategies have remained relatively simplistic, typically relying on direct actor policy rollouts. In contrast, we propose \pachs{} (\textit{P}arallel \textit{A}ctor-\textit{C}ritic \textit{H}euristic \textit{S}earch), an efficient parallel best-first search algorithm for inference that leverages both components of the actor-critic architecture: the actor network generates actions, while the critic network provides cost-to-go estimates to guide the search. Two levels of parallelism are employed within the search -- actions and cost-to-go estimates are generated in batches by the actor and critic networks respectively, and graph expansion is distributed across multiple threads. We demonstrate the effectiveness of our approach in robotic manipulation tasks, including collision-free motion planning and contact-rich interactions such as non-prehensile pushing.},
+  eprint       = {2509.25402},
+  archiveprefix = {arXiv},
+  primaryclass = {cs.RO},
+  year         = 2025,
+  pdf          = {https://arxiv.org/abs/2509.25402},
+  projects     = {implicit},
+  note         = {Under Review},
+  abbr         = {ARXIV}
+}
 @misc{meng2025look,
   title        = {Look as You Leap: Planning Simultaneous Motion and Perception for High-{DoF} Robots},
   author       = {Qingxi Meng and Emiliano Flores and Carlos Quintero-Peña and Peizhu Qian and Zachary Kingston and Shannan K. Hamlin and Vaibhav Unhelkar and Lydia E. Kavraki},
-  abstract     = {     In this work, we address the problem of planning robot motions for a high-degree-of-freedom (DoF) robot that effectively achieves a given perception task while the robot and the perception target move in a dynamic environment. Achieving navigation and perception tasks simultaneously is challenging, as these objectives often impose conflicting requirements. Existing methods that compute motion under perception constraints fail to account for obstacles, are designed for low-DoF robots, or rely on simplified models of perception. Furthermore, in dynamic real-world environments, robots must replan and react quickly to changes and directly evaluating the quality of perception (e.g., object detection confidence) is often expensive or infeasible at runtime. This problem is especially important in human-centered environments such as homes and hospitals, where effective perception is essential for safe and reliable operation. To address these challenges, we propose a GPU-parallelized perception-score-guided probabilistic roadmap planner with a neural surrogate model (PS-PRM). The planner explicitly incorporates the estimated quality of a perception task into motion planning for high-DoF robots. Our method uses a learned model to approximate perception scores and leverages GPU parallelism to enable efficient online replanning in dynamic settings. We demonstrate that our planner, evaluated on high-DoF robots, outperforms baseline methods in both static and dynamic environments in both simulation and real-robot experiments.},
+  abstract     = {In this work, we address the problem of planning robot motions for a high-degree-of-freedom (DoF) robot that effectively achieves a given perception task while the robot and the perception target move in a dynamic environment. Achieving navigation and perception tasks simultaneously is challenging, as these objectives often impose conflicting requirements. Existing methods that compute motion under perception constraints fail to account for obstacles, are designed for low-DoF robots, or rely on simplified models of perception. Furthermore, in dynamic real-world environments, robots must replan and react quickly to changes and directly evaluating the quality of perception (e.g., object detection confidence) is often expensive or infeasible at runtime. This problem is especially important in human-centered environments such as homes and hospitals, where effective perception is essential for safe and reliable operation. To address these challenges, we propose a GPU-parallelized perception-score-guided probabilistic roadmap planner with a neural surrogate model (PS-PRM). The planner explicitly incorporates the estimated quality of a perception task into motion planning for high-DoF robots. Our method uses a learned model to approximate perception scores and leverages GPU parallelism to enable efficient online replanning in dynamic settings. We demonstrate that our planner, evaluated on high-DoF robots, outperforms baseline methods in both static and dynamic environments in both simulation and real-robot experiments.},
   eprint       = {2509.19610},
   archiveprefix = {arXiv},
   primaryclass = {cs.RO},

_data/coauthors.yml

@@ -51,6 +51,19 @@
     member: true
     url: talha
 
+"yang":
+  - firstname: ["Hanlan"]
+    member: true
+    url: hanlan
+
+"likhachev":
+  - firstname: ["Maxim"]
+    url: https://www.cs.cmu.edu/~maxim/
+
+"mishani":
+  - firstname: ["Itamar"]
+    url: https://imishani.github.io/
+
 "blumenschein":
   - firstname: ["Laura H."]
     url: "https://engineering.purdue.edu/ME/People/ptProfile?resource_id=241064"