Search results
15 results
Sort by:
Context-Based Meta Reinforcement Learning for Robust and Adaptable Peg-in-Hole Assembly Tasks
Safe Leaf Manipulation for Accurate Shape and Pose Estimation of Occluded Fruits
Compact Multi-Object Placement Using Adjacency-Aware Reinforcement Learning
weerakkodi
dengler
kreis
Menon
Shokry
Intelligent Manipulation
In cluttered scenes, and with unknown objects, typical pick and place pipelines are sub-optimal. Assembly and rearrangement tasks require flexible manipulation modes using both prehensile and non-prehensile approaches with multimodal perception.
RePAIR - Reconstructing the Past: Artificial Intelligence and Robotics Meet Cultural Heritage
The 'RePAIR' project combines Artificial Intelligence and Robotics with Cultural Heritage to create technology that simplifies the reconstruction of shattered artworks. This innovation aims to address the challenge of piecing together damaged or incomplete ancient artifacts like vases, amphorae, and frescoes, often found in fragments at excavation sites worldwide.
Viewpoint Push Planning for Mapping of Unknown Confined Spaces
Learning Goal-Directed Non-Prehensile Pushing in Cluttered Scenes
Learning Goal-Directed Object Pushing in Cluttered Scenes with Location-Based Attention
HortiBot: An Adaptive Multi-Arm System for Robotic Horticulture of Sweet Peppers
Horticultural tasks such as pruning and selective harvesting are labor intensive and horticultural staff are hard to find. Automating these tasks is challenging due to the semi-structured greenhouse workspaces, changing environmental conditions such as lighting, dense plant growth with many occlusions, and the need for gentle manipulation of non-rigid plant organs. In this work, we present the three-armed system HortiBot, with two arms for manipulation and a third arm as an articulated head for active perception using stereo cameras. Its perception system detects not only peppers, but also peduncles and stems in real time, and performs online data association to build a world model of pepper plants. Collision-aware online trajectory generation allows all three arms to safely track their respective targets for observation, grasping, and cutting. We integrated perception and manipulation to perform selective harvesting of peppers and evaluated the system in lab experiments. Using active perception coupled with end-effector force torque sensing for compliant manipulation, HortiBot achieves high success rates.