AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs

Jianing Qian, Qinhe Peng, Emmanuel Panov, Leonor Fermoselle, Dinesh Jayaraman, Bernadette Bucher, Tarik Kelestemur

CVPR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
condition diffusion policy on a dynamic task-relevant scene graph instead of RGB onlyDiffusion Policy · Simulated mobile manipulation (Throw Trash, Heat-up Tea, Heat-up Tea Long)task success rateImproved
add memory of object nodes (scene graph) versus instantaneous visible-object representationDiffusion Policy · Real-world tabletop Feed-Animalstask success rateImproved
use scene graph memory for Feed-Giraffe and Clean-TableDiffusion Policy · Real-world tabletop Feed-Giraffe, Clean-Tabletask success rateImproved
increase history frames to 10 and predict past and future actions (PTP)Diffusion Policy · Simulated Heat-up Tea taskstask success rateMixed
use object-centric representations of visible objects only instead of raw RGBDiffusion Policy · Real-world Pineapple-Bowltask success rateImproved
add 3D centroid to scene graph nodes (ablation)Scene graph policy · Simulated mobile manipulation, later subtasks and final tasktask success rateImproved
add 2D and 3D object location information to scene graph nodes (ablation)Scene graph policy · Simulated mobile manipulation, later subtasks and final tasktask success rateImproved
add 3D centroid or object locations to scene graph nodes (ablation)Scene graph policy · Simulated mobile manipulation, first subtaskfirst subtask success rateNo clear effect
add 3D centroid or object locations to scene graph nodes (ablation)Scene graph policy · Real-world Pineapple-Bowl, placing in bowltask success rateNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy