{"id":40878,"date":"2026-09-17T11:15:54","date_gmt":"2026-09-17T11:15:54","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/sg-amp-scene-graph-guided-active-perception-and-semantics-aware-motion-planning-for-pepper-plants\/"},"modified":"2026-09-17T11:15:54","modified_gmt":"2026-09-17T11:15:54","slug":"sg-amp-scene-graph-guided-active-perception-and-semantics-aware-motion-planning-for-pepper-plants","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/sg-amp-scene-graph-guided-active-perception-and-semantics-aware-motion-planning-for-pepper-plants\/","title":{"rendered":"SG-AMP: Scene-Graph-Guided Active Perception and Semantics-Aware Motion Planning for Pepper Plants"},"content":{"rendered":"<p>Robots operating in dense horticulture settings such as pepper plants must perceive small, occluded plant structures while moving itself safely through the plant. We present SG-AMP, integrating robust depth completion with input-conditioned uncertainty, persistent panoptic mapping, plant scene-graph reasoning, and semantics-aware active view- motion planning. Beyond inspecting uncertain observed regions, the scene graph explicitly hypothesizes unobserved pepper\u2013peduncle attachments and directs close-range sensing toward them. Candidate views are selected according to expected information gain, while class-dependent motion costs distinguish protected peppers, peduncles, and stems from conditionally traversable foliage. On pepper data, the perception network achieves 55.27\\% semantic mIoU, 38.67\\% PQ, and 40.62 mm depth RMSE, while input-conditioned uncertainty improves NYUv2 NLL from &#8211;1.6518 to &#8211;1.6925 and AUSE from 0.0102 to 0.0087.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Robots operating in dense horticulture settings such as pepper plants must perceive small, occluded plant structures while moving itself safely through the plant. We present SG-AMP, integrating robust depth completion with input-conditioned uncertainty, persistent panoptic mapping, plant scene-graph reasoning, and semantics-aware active view- motion planning. Beyond inspecting uncertain observed regions, the scene graph explicitly hypothesizes unobserved pepper\u2013peduncle attachments and directs close-range sensing toward them. Candidate views are selected according to [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[30],"class_list":["post-40878","publication","type-publication","status-publish","hentry","publication-type-article"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/40878","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/40878\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=40878"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=40878"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}