arXiv subjects

Domenico Campolo

Publications and source records attributed to Domenico Campolo.

22 records · Page 2Linked to original sources

arXiv2025

Path Planning in Complex Environments with Superquadrics and Voronoi-Based Orientation

Path planning in narrow passages is a challenging problem in various applications. Traditional planning algorithms often face challenges in complex environments like mazes and traps, where narrow entrances require special orientation control for successful navigation. In this work, we present a novel approach that combines superquadrics (SQ) representation and Voronoi diagrams to solve the narrow passage problem in both 2D and 3D environment. Our method utilizes the SQ formulation to expand obstacles, eliminating impassable passages, while Voronoi hyperplane ensures maximum clearance path. Additionally, the hyperplane provides a natural reference for robot orientation, aligning its long axis with the passage direction. We validate our framework through a 2D object retrieval task and 3D drone simulation, demonstrating that our approach outperforms classical planners and a cutting-edge drone planner by ensuring passable trajectories with maximum clearance.

cs.RO↗

arXiv2024

Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives

Devising deep latent variable models for multi-modal data has been a long-standing theme in machine learning research. Multi-modal Variational Autoencoders (VAEs) have been a popular generative model class that learns latent representations that jointly explain multiple modalities. Various objective functions for such models have been suggested, often motivated as lower bounds on the multi-modal data log-likelihood or from information-theoretic considerations. To encode latent variables from different modality subsets, Product-of-Experts (PoE) or Mixture-of-Experts (MoE) aggregation schemes have been routinely used and shown to yield different trade-offs, for instance, regarding their generative quality or consistency across multiple modalities. In this work, we consider a variational objective that can tightly approximate the data log-likelihood. We develop more flexible aggregation schemes that avoid the inductive biases in PoE or MoE approaches by combining encoded features from different modalities based on permutation-invariant neural networks. Our numerical experiments illustrate trade-offs for multi-modal variational objectives and various aggregation schemes. We show that our variational objective and more flexible aggregation models can become beneficial when one wants to approximate the true joint distribution over observed modalities and latent variables in identifiable models.

stat.ML↗

arXiv2024

A Basic Mechanical and Geometric Framework for Quasi-Static Manipulation

In this work, we propose a geometric framework for analyzing mechanical manipulation, for instance, by a robotic agent. Under the assumption of conservative forces and quasi-static manipulation, we use energy methods to derive a metric. In the first part of the paper, we review how quasi-static mechanical manipulation tasks can be naturally described via the so-called force-space, i.e. the cotangent bundle of the configuration space, and its Lagrangian submanifolds. Then, via a second order analysis, we derive the control Hessian of total energy. As this is not necessarily positive-definite, from an optimal control perspective, we propose the use of the squared-Hessian, also motivated by insights derived from both mechanics (Gauss' Principle) and biology (Separation Principle). In the second part of the paper, we apply such methods to the problem of an elastically-driven, inverted pendulum. Despite its apparent simplicity, this example is representative of an important class of robotic manipulation problems for which we show how a smooth elastic potential can be derived by regularizing mechanical contact. We then show how graph theory can be used to connect each numerical solution to `nearby' ones, with weights derived from the very metric introduced in the first part of the paper.

math.OC↗

arXiv2022

GloCAL: Glocalized Curriculum-Aided Learning of Multiple Tasks with Application to Robotic Grasping

The domain of robotics is challenging to apply deep reinforcement learning due to the need for large amounts of data and for ensuring safety during learning. Curriculum learning has shown good performance in terms of sample- efficient deep learning. In this paper, we propose an algorithm (named GloCAL) that creates a curriculum for an agent to learn multiple discrete tasks, based on clustering tasks according to their evaluation scores. From the highest-performing cluster, a global task representative of the cluster is identified for learning a global policy that transfers to subsequently formed new clusters, while the remaining tasks in the cluster are learned as local policies. The efficacy and efficiency of our GloCAL algorithm are compared with other approaches in the domain of grasp learning for 49 objects with varied object complexity and grasp difficulty from the EGAD! dataset. The results show that GloCAL is able to learn to grasp 100% of the objects, whereas other approaches achieve at most 86% despite being given 1.5 times longer training time.

cs.RO↗