Francis wyffels

Thomas Lips, Victor-Louis De Gusseme, Francis wyffels

Robotic cloth manipulation is challenging due to its deformability, which makes determining its full state infeasible. However, for cloth folding, it suffices to know the position of a few semantic keypoints. Convolutional neural networks (CNN) can be used to detect these keypoints, but require large amounts of annotated data, which is expensive to collect. To overcome this, we propose to learn these keypoint detectors purely from synthetic data, enabling low-cost data collection. In this paper, we procedurally generate images of towels and use them to train a CNN. We evaluate the performance of this detector for folding towels on a unimanual robot setup and find that the grasp and fold success rates are 77% and 53%, respectively. We conclude that learning keypoint detectors from synthetic data for cloth folding and related tasks is a promising research direction, discuss some failures and relate them to future work. A video of the system, as well as the codebase, more details on the CNN architecture and the training setup can be found at https://github.com/tlpss/workshop-icra-2022-cloth-keypoints.git.

Thomas Lips, Marco Moletta, Michael C. Welle et al.

RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representations to improve generalization for robotic manipulation. Visual foundation models enable one-shot extraction of keypoints to provide such representation. However, it remains unclear how to integrate them into imitation learning optimally and when they outperform alternative representations. We combine approaches from previous works on keypoint imitation learning (KIL) and investigate several design choices to provide practical guidelines. Using over 2000 real-world rollouts, we also assess the generalization capabilities of KIL to unseen objects and scene variations. KIL achieves a 75% overall success rate across five tasks, significantly outperforming the RGB baseline (47%) and performing on par with S2-diffusion (73%). Finally, we explore the limitations of the foundation models used for keypoint extraction and extend KIL to tasks with multiple object instances. Our results confirm KIL as a data-efficient approach for robot learning, though it does not outperform alternative representations and inherits limitations of the foundation models used for keypoint extraction. All rollout videos, demonstrations, and results are available at https://kil-manipulation.github.io/.

Rembert Daems, Jeroen Taets, Francis wyffels et al.

We present KeyCLD, a framework to learn Lagrangian dynamics from images. Learned keypoints represent semantic landmarks in images and can directly represent state dynamics. We show that interpreting this state as Cartesian coordinates, coupled with explicit holonomic constraints, allows expressing the dynamics with a constrained Lagrangian. KeyCLD is trained unsupervised end-to-end on sequences of images. Our method explicitly models the mass matrix, potential energy and the input matrix, thus allowing energy based control. We demonstrate learning of Lagrangian dynamics from images on the dm_control pendulum, cartpole and acrobot environments. KeyCLD can be learned on these systems, whether they are unactuated, underactuated or fully actuated. Trained models are able to produce long-term video predictions, showing that the dynamics are accurately learned. We compare with Lag-VAE, Lag-caVAE and HGN, and investigate the benefit of the Lagrangian prior and the constraint function. KeyCLD achieves the highest valid prediction time on all benchmarks. Additionally, a very straightforward energy shaping controller is successfully applied on the fully actuated systems. Please refer to our project page for code and additional results: https://rdaems.github.io/keycld/

Remko Proesmans, Thomas Lips, Francis wyffels

Large behaviour models have transformed the field of robotic manipulation, but prohibitive data requirements have thus far prevented a revolution similar to vision language models. We believe that instrumentation, i.e. sensor integration in objects, can provide invaluable state information and enable efficient learning for robotic manipulation. In this paper, we present instrumented imitation learning of clothes hanger insertion. Using 180 teleoperated demonstrations, we train diffusion policies with and without access to instrumentation data. Results show that policies leveraging instrumentation outperform vision-only counterparts by 14-25 %pt and exhibit greater task awareness. Crucially, a black-box imitation learning policy learns to prioritise instrumentation signals without explicit guidance. In addition, enhancing the teleoperation dataset with rollouts from an instrumented expert policy, enables a vision-only student policy to achieve performance comparable to the instrumented expert, thereby surpassing the original vision-only policy. These findings establish instrumentation as a promising strategy to enhance imitation learning for robotic manipulation. Datasets are available on Zenodo.

Peter De Roovere, Steven Moonen, Nick Michiels et al.

We present a diverse dataset of industrial metal objects. These objects are symmetric, textureless and highly reflective, leading to challenging conditions not captured in existing datasets. Our dataset contains both real-world and synthetic multi-view RGB images with 6D object pose labels. Real-world data is obtained by recording multi-view images of scenes with varying object shapes, materials, carriers, compositions and lighting conditions. This results in over 30,000 images, accurately labelled using a new public tool. Synthetic data is obtained by carefully simulating real-world conditions and varying them in a controlled and realistic way. This leads to over 500,000 synthetic images. The close correspondence between synthetic and real-world data, and controlled variations, will facilitate sim-to-real research. Our dataset's size and challenging nature will facilitate research on various computer vision tasks involving reflective materials. The dataset and accompanying resources are made available on the project website at https://pderoovere.github.io/dimo.

Peter De Roovere, Rembert Daems, Jonathan Croenen et al.

We introduce CenDerNet, a framework for 6D pose estimation from multi-view images based on center and curvature representations. Finding precise poses for reflective, textureless objects is a key challenge for industrial robotics. Our approach consists of three stages: First, a fully convolutional neural network predicts center and curvature heatmaps for each view; Second, center heatmaps are used to detect object instances and find their 3D centers; Third, 6D object poses are estimated using 3D centers and curvature heatmaps. By jointly optimizing poses across views using a render-and-compare approach, our method naturally handles occlusions and object symmetries. We show that CenDerNet outperforms previous methods on two industry-relevant datasets: DIMO and T-LESS.

Thomas Lips, Victor-Louis De Gusseme, Francis wyffels

Assistive robots should be able to wash, fold or iron clothes. However, due to the variety, deformability and self-occlusions of clothes, creating robot systems for cloth manipulation is challenging. Synthetic data is a promising direction to improve generalization, but the sim-to-real gap limits its effectiveness. To advance the use of synthetic data for cloth manipulation tasks such as robotic folding, we present a synthetic data pipeline to train keypoint detectors for almost-flattened cloth items. To evaluate its performance, we have also collected a real-world dataset. We train detectors for both T-shirts, towels and shorts and obtain an average precision of 64% and an average keypoint distance of 18 pixels. Fine-tuning on real-world data improves performance to 74% mAP and an average distance of only 9 pixels. Furthermore, we describe failure modes of the keypoint detectors and compare different approaches to obtain cloth meshes and materials. We also quantify the remaining sim-to-real gap and argue that further improvements to the fidelity of cloth assets will be required to further reduce this gap. The code, dataset and trained models are available

Qiaoqiao Ren, Remko Proesmans, Yuanbo Hou et al.

Human emotions are complex and can be conveyed through nuanced touch gestures. Previous research has primarily focused on how humans recognize emotions through touch or on identifying key features of emotional expression for robots. However, there is a gap in understanding how reliably these emotions and gestures can be communicated to robots via touch and interpreted using data driven methods. This study investigates the consistency and distinguishability of emotional and gestural expressions through touch and sound. To this end, we integrated a custom piezoresistive pressure sensor as well as a microphone on a social robot. Twenty-eight participants first conveyed ten different emotions to the robot using spontaneous touch gestures, then they performed six predefined social touch gestures. Our findings reveal statistically significant consistency in both emotion and gesture expression among participants. However, some emotions exhibited low intraclass correlation values, and certain emotions with similar levels of arousal or valence did not show significant differences in their conveyance. To investigate emotion and social gesture decoding within affective human-robot tactile interaction, we developed single-modality models and multimodal models integrating tactile and auditory features. A support vector machine (SVM) model trained on multimodal features achieved the highest accuracy for classifying ten emotions, reaching 40 %.For gesture classification, a Convolutional Neural Network- Long Short-Term Memory Network (CNN-LSTM) achieved 90.74 % accuracy. Our results demonstrate that even though the unimodal models have the potential to decode emotions and touch gestures, the multimodal integration of touch and sound significantly outperforms unimodal approaches, enhancing the decoding of both emotions and gestures.

Raman Talwar, Remko Proesmans, Thomas Lips et al.

Learning contact-rich manipulation is difficult from cameras and proprioception alone because contact events are only partially observed. We test whether training-time instrumentation, i.e., object sensorisation, can improve policy performance without creating deployment-time dependencies. Specifically, we study button pressing as a testbed and use a microphone fingertip to capture contact-relevant audio. We use an instrumented button-state signal as privileged supervision to fine-tune an audio encoder into a contact event detector. We combine the resulting representation with imitation learning using three strategies, such that the policy only uses vision and audio during inference. Button press success rates are similar across methods, but instrumentation-guided audio representations consistently reduce contact force. These results support instrumentation as a practical training-time auxiliary objective for learning contact-rich manipulation policies.

Thomas Lips, Francis wyffels

Robots that assist humans will need to interact with articulated objects such as cabinets or microwaves. Early work on creating systems for doing so used proprioceptive sensing to estimate joint mechanisms during contact. However, nowadays, almost all systems use only vision and no longer consider proprioceptive information during contact. We believe that proprioceptive information during contact is a valuable source of information and did not find clear motivation for not using it in the literature. Therefore, in this paper, we create a system that, starting from a given grasp, uses proprioceptive sensing to open cabinets with a position-controlled robot and a parallel gripper. We perform a qualitative evaluation of this system, where we find that slip between the gripper and handle limits the performance. Nonetheless, we find that the system already performs quite well. This poses the question: should we make more use of proprioceptive information during contact in articulated object manipulation systems, or is it not worth the added complexity, and can we manage with vision alone? We do not have an answer to this question, but we hope to spark some discussion on the matter. The codebase and videos of the system are available at https://tlpss.github.io/revisiting-proprioception-for-articulated-manipulation/.

Alexander Vandesompele, Gabriel Urbain, Francis wyffels et al.

Compliant robots can be more versatile than traditional robots, but their control is more complex. The dynamics of compliant bodies can however be turned into an advantage using the physical reservoir computing frame-work. By feeding sensor signals to the reservoir and extracting motor signals from the reservoir, closed loop robot control is possible. Here, we present a novel framework for implementing central pattern generators with spiking neural networks to obtain closed loop robot control. Using the FORCE learning paradigm, we train a reservoir of spiking neuron populations to act as a central pattern generator. We demonstrate the learning of predefined gait patterns, speed control and gait transition on a simulated model of a compliant quadrupedal robot.

Gabriel Urbain, Victor Barasuol, Claudio Semini et al.

Advances in legged robotics are strongly rooted in animal observations. A clear illustration of this claim is the generalization of Central Pattern Generators (CPG), first identified in the cat spinal cord, to generate cyclic motion in robotic locomotion. Despite a global endorsement of this model, physiological and functional experiments in mammals have also indicated the presence of descending signals from the cerebellum, and reflex feedback from the lower limb sensory cells, that closely interact with CPGs. To this day, these interactions are not fully understood. In some studies, it was demonstrated that pure reflex-based locomotion in the absence of oscillatory signals could be achieved in realistic musculoskeletal simulation models or small compliant quadruped robots. At the same time, biological evidence has attested the functional role of the cerebellum for predictive control of balance and stance within mammals. In this paper, we promote both approaches and successfully apply reflex-based dynamic locomotion, coupled with a balance and gravity compensation mechanism, on the state-of-art HyQ robot. We discuss the importance of this stability module to ensure a correct foot lift-off and maintain a reliable gait. The robotic platform is further used to test two different architectural hypotheses inspired by the cerebellum. An analysis of experimental results demonstrates that the most biologically plausible alternative also leads to better results for robust locomotion.

Jonas Degrave, Michiel Hermans, Joni Dambre et al.

An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent. When gradient-based methods are used, models are kept small or rely on finite difference approximations for the Jacobian. This method quickly grows expensive with increasing numbers of parameters, such as found in deep learning. We propose the implementation of a modern physics engine, which can differentiate control parameters. This engine is implemented for both CPU and GPU. Firstly, this paper shows how such an engine speeds up the optimization process, even for small problems. Furthermore, it explains why this is an alternative approach to deep Q-learning, for using deep learning in robotics. Finally, we argue that this is a big step for deep learning in robotics, as it opens up new possibilities to optimize robots, both in hardware and software.

Francis wyffels, Willem Van de Steene, Jelle Roets et al.

There is an increasing worldwide demand for people educated into science and technology. Unfortunately, girls and underprivileged students are often underrepresented in Science, Technology, Engineering and Mathematics (STEM) education programs. We believe that by inclusion of art in these programs, educational activities might become more attractive to a broader audience. In this work we present an example of such an educational activity: an international robotics and art week for secondary school students. This educational activity builds up on the project-based and inquiry learning framework. This article is intended as a brief manual to help others organise such an activity. It also gives insights in how we led a highly heterogeneous group of students into learning STEM and becoming science and technology ambassadors for their peers.