7 papers · 1 filter
MoDex: A Diffusion Policy for Sequential Multi-Object Dexterous Grasping
Haofei Lu, Hongjia Liu, Yifei Dong +3
This work addresses sequentially grasping multiple objects with a single dexterous hand without releasing those already held. Most dexterous grasping methods commit all of the hand…
Reduced-order Control and Geometric Structure of Learned Lagrangian Latent Dynamics
Katharina Friedl, Noémie Jaquier, Seungyeon Kim +2
Model-based controllers can offer strong guarantees on stability and convergence by relying on physically accurate dynamic models. However, these are rarely available for high-dime…
FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions
Daniel Marta, Simon Holk, Miguel Vasco +6
Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user prefere…
Pushing Everything Everywhere All At Once: Probabilistic Prehensile Pushing
Patrizio Perugini, Jens Lundell, Katharina Friedl +1
We address prehensile pushing, the problem of manipulating a grasped object by pushing against the environment. Our solution is an efficient nonlinear trajectory optimization probl…
Grasping a Handful: Sequential Multi-Object Dexterous Grasp Generation
Haofei Lu, Yifei Dong, Zehang Weng +3
We introduce the sequential multi-object robotic grasp sampling algorithm SeqGrasp that can robustly synthesize stable grasps on diverse objects using the robotic hand's partial De…
DexDiffuser: Generating Dexterous Grasps with Diffusion Models
Zehang Weng, Haofei Lu, Danica Kragic +1
We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffu…
CAPGrasp: An Continuous Approach-Constrained Generative Grasp Sampler
Zehang Weng, Haofei Lu, Jens Lundell +1
We propose CAPGrasp, an 6-DoF continuous approach-constrained generative grasp sampler. It includes a novel learning strategy for trai…