AIConfPaper
← Search

Lionel Ott

57 accepted papers

2026

InstantPose: Zero-Shot Instance-Level 6D Pose Estimation from a Single View

Francesco Di Felice, Alberto Remus, Stefano Gasperini, Benjamin Busam, Lionel Ott, Stefan Thalhammer +2
ICRA 2026poster

Object pose estimation using visual data is crucial for robotic interaction with the environment. Many existing instance-level methods are restricted by their requirements for 3D CAD models or multiple object views, which limits their flexibility and generalizability. Overcoming this limitation is c…

Cited by 0Source ↗Scholar ↗
2025

CueLearner: Bootstrapping and local policy adaptation from relative feedback

Giulio Schiavi, Andrei Cramariuc, Lionel Ott, Roland Siegwart
IROS 2025

Human guidance has emerged as a powerful tool for enhancing reinforcement learning (RL). However, conventional forms of guidance such as demonstrations or binary scalar feedback can be challenging to collect or have low information content, motivating the exploration of other forms of human input. A

Cited by 0Source ↗Scholar ↗
2025

Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids

Victor Reijgwart, Cesar Cadena, Roland Siegwart, Lionel Ott
RSS 2025poster

Hierarchical, multi-resolution volumetric mapping approaches are widely used to represent large and complex environments as they can efficiently capture their occupancy and connectivity information. Yet widely used path planning methods such as sampling and trajectory optimization do not exploit thi…

Cited by 0PDF ↗Scholar ↗
2025

InstantPose: Zero-Shot Instance-Level 6D Pose Estimation From a Single View

Francesco Di Felice, Alberto Remus, Stefano Gasperini, Benjamin Busam, Lionel Ott, Stefan Thalhammer +2
RA-L 2025

Object pose estimation using visual data is crucial for robotic interaction with the environment. Many existing instance-level methods are restricted by their requirements for 3D CAD models or multiple object views, which limits their flexibility and generalizability. Overcoming this limitation is c

Cited by 4Source ↗Scholar ↗
2024

NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models

Francesco Milano, Jen Jen Chung, Hermann Blum, Roland Siegwart, Lionel Ott
IROS 2024poster

State-of-the-art approaches for 6D object pose estimation assume the availability of CAD models and require the user to manually set up physically-based rendering (PBR) pipelines for synthetic training data generation. Both factors limit the application of these methods in real-world scenarios. In t…

Cited by 2Source ↗code ↗Scholar ↗
2024

On Learning Scene-aware Generative State Abstractions for Task-level Mobile Manipulation Planning

Julian Förster, Jen Jen Chung, Lionel Ott, Roland Siegwart
IROS 2024

Task and motion planning (TAMP) is a promising approach for efficient long-horizon manipulation planning, which is a prerequisite for being able to deploy manipulation systems in human-centered environments at scale. TAMP systems often rely on so-called predicates to abstractly describe the world. T

Cited by 1Source ↗code ↗Scholar ↗
2024

Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration

Abby O'Neill, Abdul Rehman, Abhiram Maddukuri, Abhishek Gupta, Abhishek Padalkar, Abraham Lee +273
ICRA 2024

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for man

Cited by 910Source ↗code ↗Scholar ↗
2024

Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration0

Abby O’Neill, Abdul Rehman, Abhiram Maddukuri, Abhishek Gupta, Abhishek Padalkar, Abraham Lee +273
ICRA 2024poster

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for man…

Cited by 259Source ↗code ↗Scholar ↗
2024

Task Adaptation in Industrial Human-Robot Interaction: Leveraging Riemannian Motion Policies

Mike Allenspach, Michael Pantic, Rik Girod, Lionel Ott, Roland Siegwart
RSS 2024poster

In real-world industrial environments, modern robots often rely on human operators for crucial decision-making and mission synthesis from individual tasks. Effective and safe collaboration between humans and robots requires systems that can adjust their motion to human intentions, enabling dynamic t…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Waverider: Leveraging Hierarchical, Multi-Resolution Maps for Efficient and Reactive Obstacle Avoidance

Victor Reijgwart, Michael Pantic, Roland Siegwart, Lionel Ott
ICRA 2024

Fast and reliable obstacle avoidance is an important task for mobile robots. In this work, we propose an efficient reactive system that provides high-quality obstacle avoidance while running at hundreds of hertz with minimal resource usage. Our approach combines wavemap, a hierarchical volumetric ma

Cited by 8Source ↗Scholar ↗
2024

Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation

Francesco Di Felice, Alberto Remus, Stefano Gasperini, Benjamin Busam, Lionel Ott, Federico Tombari +2
IROS 2024

Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture t

Cited by 13Source ↗Scholar ↗
2023

Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps

Kenneth Blomqvist, Lionel Ott, Jen Jen Chung, Roland Siegwart
IROS 2023poster

Methods have recently been proposed that densely segment 3D volumes into classes using only color images and expert supervision in the form of sparse semantically annotated pixels. While impressive, these methods still require a relatively large amount of supervision and segmenting an object can tak…

Cited by 9Source ↗Scholar ↗
2023

Efficient volumetric mapping of multi-scale environments using wavelet-based compression

Victor Reijgwart, Cesar Cadena, Roland Siegwart, Lionel Ott
RSS 2023poster

Volumetric maps are widely used in robotics due to their desirable properties in applications such as path planning, exploration, and manipulation. Constant advances in mapping technologies are needed to keep up with the improvements in sensor technology, generating increasingly vast amounts of prec…

Cited by 15Source ↗PDF ↗code ↗Scholar ↗
2023

Learning Agent-Aware Affordances for Closed-Loop Interaction with Articulated Objects

Giulio Schiavi, Paula Wulkop, Giuseppe Rizzi, Lionel Ott, Roland Siegwart, Jen Jen Chung
ICRA 2023poster

Interactions with articulated objects are a challenging but important task for mobile robots. To tackle this challenge, we propose a novel closed-loop control pipeline, which integrates manipulation priors from affordance estimation with sampling-based whole-body control. We introduce the concept of…

Cited by 22Source ↗code ↗Scholar ↗
2023

Material-Agnostic Shaping of Granular Materials with Optimal Transport

Nikhilesh Alatur, Olov Andersson, Roland Siegwart, Lionel Ott
IROS 2023poster

From construction materials, such as sand or asphalt, to kitchen ingredients, like rice, sugar, or salt; the world is full of granular materials. Despite impressive progress in robotic manipulation of single objects, granular materials remain a challenge due to difficulties in modelling these highly…

Cited by 0Source ↗Scholar ↗
2023

NeRFing it: Offline Object Segmentation Through Implicit Modeling

Kenneth Blomqvist, Jen Jen Chung, Lionel Ott, Roland Siegwart
ICRA 2023poster

Most recently proposed methods for robotic per-ception are based on deep learning, which require very large datasets to perform well. The accuracy of a learned model is mainly dependent on the data distribution it was trained on. Thus for deploying such models, it is crucial to use training data bel…

Cited by 1Source ↗Scholar ↗
2023

Neural Implicit Vision-Language Feature Fields

Kenneth Blomqvist, Francesco Milano, Jen Jen Chung, Lionel Ott, Roland Siegwart
IROS 2023poster

Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided at run-time in the form of text prompts, as opposed to a fixed set of classes defined at training time. In this work, we…

Cited by 12Source ↗code ↗Scholar ↗
2023

Obstacle avoidance using Raycasting and Riemannian Motion Policies at kHz rates for MAVs

Michael Pantic, Isar Meijer, Rik Bähnemann, Nikhilesh Alatur, Olov Andersson, Cesar Cadena +2
ICRA 2023poster

This paper presents a novel method for using Riemannian Motion Policies on volumetric maps, shown in the example of obstacle avoidance for Micro Aerial Vehicles (MAVs), Today, most robotic obstacle avoidance algorithms rely on sampling or optimization-based planners with volumetric maps. However, th…

Cited by 16Source ↗code ↗Scholar ↗
2023

SphNet: A Spherical Network for Semantic Pointcloud Segmentation

Lukas Bernreiter, Lionel Ott, Roland Siegwart, Cesar Cadena
ICRA 2023poster

Semantic segmentation for robotic systems can enable a wide range of applications, from self-driving cars and augmented reality systems to domestic robots. We argue that a spherical representation is a natural one for egocentric pointclouds. Thus, in this work, we present a novel framework exploitin…

Cited by 2Source ↗Scholar ↗
2022

Aerial Layouting: Design and Control of a Compliant and Actuated End-Effector for Precise In-flight Marking on Ceilings

Christian Lanegger, Marco Ruggia, Marco Tognon, Lionel Ott, Roland Siegwart
RSS 2022poster

Aerial robots have demonstrated impressive feats of precise control, such as dynamic flight through openings or highly complex choreographies. Despite the accuracy needed for these tasks, there are problems that require levels of precision that are challenging to achieve today. One such problem is a…

Cited by 12Source ↗PDF ↗Scholar ↗
2022

Autonomous Teamed Exploration of Subterranean Environments using Legged and Aerial Robots

Mihir Kulkarni, Mihir Dharmadhikari, Marco Tranzatto, Samuel Zimmermann, Victor Reijgwart, Paolo De Petris +7
ICRA 2022poster

This paper presents a novel strategy for autonomous teamed exploration of subterranean environments using legged and aerial robots. Tailored to the fact that subterranean settings, such as cave networks and underground mines, often involve complex, large-scale and multi-branched topologies, while wi…

Cited by 112Source ↗code ↗Scholar ↗
2022

Closed-Loop Next-Best-View Planning for Target-Driven Grasping

Michel Breyer, Lionel Ott, Roland Siegwart, Jen Jen Chung
IROS 2022poster

Picking a specific object from clutter is an essential component of many manipulation tasks. Partial observations often require the robot to collect additional views of the scene before attempting a grasp. This paper proposes a closed-loop next-best-view planner that drives exploration based on occl…

Cited by 29Source ↗code ↗Scholar ↗
2022

Collaborative Robot Mapping using Spectral Graph Analysis

Lukas Bernreiter, Shehryar Khattak, Lionel Ott, Roland Siegwart, Marco Hutter, Cesar Cadena
ICRA 2022poster

In this paper, we deal with the problem of creating globally consistent pose graphs in a centralized multi-robot SLAM framework. For each robot to act autonomously, individual onboard pose estimates and maps are maintained, which are then communicated to a central server to build an optimized global…

Cited by 15Source ↗Scholar ↗
2022

Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks

Weiming Zhi, Tin Lai, Lionel Ott, Edwin V. Bonilla, Fabio Ramos
ICML 2022spotlight

Advances in differentiable numerical integrators have enabled the use of gradient descent techniques to learn ordinary differential equations (ODEs), where a flexible function approximator (often a neural network) is used to estimate the system dynamics, given as a time derivative. However, these in…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2022

Learning Variable Impedance Control for Aerial Sliding on Uneven Heterogeneous Surfaces by Proprioceptive and Tactile Sensing

Weixuan Zhang, Lionel Ott, Marco Tognon, Roland Siegwart
RA-L 2022

The recent development of novel aerial vehicles capable of physically interacting with the environment leads to new applications such as contact-based inspection. These tasks require the robotic system to exchange forces with partially-known environments, which may contain uncertainties including un

Cited by 28Source ↗Scholar ↗
2022

Visual Loop Closure Detection for a Future Mars Science Helicopter

Alexander Dietsche, Lionel Ott, Roland Siegwart, Roland Brockers
RA-L 2022

Future Mars Rotorcrafts will require the ability to precisely navigate to previously visited locations in order to return to a safe landing site or execute precise scientific measurements, such as sample acquisition or targeted sensing. To enable a future Mars Science Helicopter to perform in-flight

Cited by 0Source ↗Scholar ↗
2021

A Unified Approach for Autonomous Volumetric Exploration of Large Scale Environments Under Severe Odometry Drift

Lukas Schmid, Victor Reijgwart, Lionel Ott, Juan I. Nieto, Roland Siegwart, César Cadena
RA-L 2021

Exploration is a fundamental problem in robot autonomy. A major limitation, however, is that during exploration robots oftentimes have to rely on on-board systems alone for state estimation, accumulating significant drift over time in large environments. Drift can be detrimental to robot safety and

Cited by 36Source ↗code ↗Scholar ↗
2021

Active Model Learning using Informative Trajectories for Improved Closed-Loop Control on Real Robots

Weixuan Zhang, Marco Tognon, Lionel Ott, Roland Siegwart, Juan Nieto
ICRA 2021poster

Model-based controllers on real robots require accurate knowledge of the system dynamics to perform optimally. For complex dynamics, first-principles modeling is not sufficiently precise, and data-driven approaches can be leveraged to learn a statistical model from real experiments. However, the eff…

Cited by 11Source ↗Scholar ↗
2021

Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements

Weiming Zhi, Tin Lai, Lionel Ott, Fabio Ramos
ICRA 2021poster

Critical for the coexistence of humans and robots in dynamic environments is the capability for agents to understand each other’s actions, and anticipate their movements. This paper presents Stochastic Process Anticipatory Navigation (SPAN), a framework that enables nonholonomic robots to navigate i…

Cited by 8Source ↗Scholar ↗
2021

Mesh Manifold Based Riemannian Motion Planning for Omnidirectional Micro Aerial Vehicles

Michael Pantic, Lionel Ott, Cesar Cadena, Roland Siegwart, Juan I. Nieto
RA-L 2021

This letter presents a novel on-line path planning method that enables aerial robots to interact with surfaces. We present a solution to the problem of finding trajectories that drive a robot towards a surface and move along it. Triangular meshes are used as a surface map representation that is free

Cited by 14Source ↗Scholar ↗
2021

PHASER: A Robust and Correspondence-Free Global Pointcloud Registration

Lukas Bernreiter, Lionel Ott, Juan I. Nieto, Roland Siegwart, Cesar Cadena
RA-L 2021

We propose PHASER, a correspondence-free global registration of sensor-centric pointclouds that is robust to noise, sparsity, and partial overlaps. Our method can seamlessly handle multimodal information, and does not rely on keypoint nor descriptor preprocessing modules. By exploiting properties of

Cited by 37Source ↗code ↗Scholar ↗
2021

Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems

Lukas Bernreiter, Lionel Ott, Juan Nieto, Roland Siegwart, Cesar Cadena
ICRA 2021poster

In this paper, we propose a robust end-to-end multi-modal pipeline for place recognition where the sensor systems can differ from the map building to the query. Our approach operates directly on images and LiDAR scans without requiring any local feature extraction modules. By projecting the sensor d…

Cited by 23Source ↗code ↗Scholar ↗
2020

An Efficient Sampling-Based Method for Online Informative Path Planning in Unknown Environments

Lukas Schmid, Michael Pantic, Raghav Khanna, Lionel Ott, Roland Siegwart, Juan I. Nieto
RA-L 2020

The ability to plan informative paths online is essential to robot autonomy. In particular, sampling-based approaches are often used as they are capable of using arbitrary information gain formulations. However, they are prone to local minima, resulting in sub-optimal trajectories, and sometimes do

Cited by 285Source ↗code ↗Scholar ↗
2020

DISCO: Double Likelihood-free Inference Stochastic Control

Lucas Barcelos, Rafael Oliveira, Rafael Possas, Lionel Ott, Fabio Ramos
ICRA 2020poster

Accurate simulation of complex physical systems enables the development, testing, and certification of control strategies before they are deployed into the real systems. As simulators become more advanced, the analytical tractability of the differential equations and associated numerical solvers inc…

Cited by 15Source ↗code ↗Scholar ↗
2020

Learning Dynamics for Improving Control of Overactuated Flying Systems

Weixuan Zhang, Maximilian Brunner, Lionel Ott, Mina Kamel, Roland Siegwart, Juan I. Nieto
RA-L 2020

Overactuated omnidirectional flying vehicles are capable of generating force and torque in any direction, which is important for applications such as contact-based industrial inspection. This comes at the price of an increase in model complexity. These vehicles usually have non-negligible, repetitiv

Cited by 14Source ↗Scholar ↗
2020

Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter

Michel Breyer, Jen Jen Chung, Lionel Ott, Roland Siegwart, Juan Nieto
CoRL 2020

General robot grasping in clutter requires the ability to synthesize grasps that work for previously unseen objects and that are also robust to physical interactions, such as collisions with other objects in the scene. In this work, we design and train a network that predicts 6 DOF grasps from 3D sc

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2019

Continuous Occupancy Map Fusion with Fast Bayesian Hilbert Maps

Weiming Zhi, Lionel Ott, Ransalu Senanayake, Fabio Ramos
ICRA 2019poster

Mapping the occupancy of an environment is central for robot autonomy. Traditional occupancy grid maps discretise the environment into independent cells, neglecting important spatial correlations, and are unable to capture the continuous nature of the real world. With these drawbacks of grid maps in…

Cited by 39Source ↗Scholar ↗
2019

Spatiotemporal Learning of Directional Uncertainty in Urban Environments With Kernel Recurrent Mixture Density Networks

Weiming Zhi, Ransalu Senanayake, Lionel Ott, Fabio Ramos
RA-L 2019

Autonomous vehicles operating in urban environments need to deal with an abundance of other dynamic objects, such as pedestrians and vehicles. This requires the development of predictive models that capture the complexity and long-term patterns of motion in the environment. We approach this problem

Cited by 42Source ↗Scholar ↗
2019

Speeding Up Iterative Closest Point Using Stochastic Gradient Descent

Fahira Afzal Maken, Fabio Ramos, Lionel Ott
ICRA 2019poster

Sensors producing 3D point clouds such as 3D laser scanners and RGB-D cameras are widely used in robotics, be it for autonomous driving or manipulation. Aligning point clouds produced by these sensors is a vital component in such applications to perform tasks such as model registration, pose estimat…

Cited by 18Source ↗code ↗Scholar ↗
2018

Learning to Race Through Coordinate Descent Bayesian Optimisation

Rafael Oliveira, Fernando H. M. Rocha, Lionel Ott, Vitor Guizilini, Fabio Ramos, Valdir Grassi
ICRA 2018poster

In the automation of many kinds of processes, the observable outcome can often be described as the combined effect of an entire sequence of actions, or controls, applied throughout the process execution. In these cases, strategies to optimise control policies for individual stages of the process are…

Cited by 13Source ↗Scholar ↗
2016

Alextrac: Affinity learning by exploring temporal reinforcement within association chains

Alex Bewley, Lionel Ott, Fabio Ramos, Ben Upcroft
ICRA 2016

This paper presents a self-supervised approach for learning to associate object detections in a video sequence as often required in tracking-by-detection systems. In this paper we focus on learning an affinity model to estimate the data association cost, which can adapt to different situations by ex

Cited by 40Source ↗Scholar ↗
2016

Spatio-Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments

Ransalu Senanayake, Lionel Ott, Simon O'Callaghan, Fabio T Ramos
NeurIPS 2016poster

We consider the problem of building continuous occupancy representations in dynamic environments for robotics applications. The problem has hardly been discussed previously due to the complexity of patterns in urban environments, which have both spatial and temporal dependencies. We address the pr…

Cited by 30Source ↗PDF ↗Scholar ↗