A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
DIGIT is a low-cost tactile sensor for in-hand manipulation.
Diffusion models enhance robotic manipulation through probabilistic multi-modal learning.
Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges, especially when using rigid position-controlled manipulators. These challenges inc…
A new reward shaping method balances learning efficiency and effectiveness for robot manipulation.
Paper presents a new port-Hamiltonian model for vehicle manipulators.
A new method for robot manipulation tasks using imagined object goals.
Deep Reinforcement Learning (DRL) has emerged as a powerful control technique in robotic science. In contrast to control theory, DRL is more robust in the thorough exploration of the environment. This capability of DRL generates more human-like behaviour and intelligence when applied to the robots. To explore this capa…
Proposes KStar Diffuser for kinematics-aware bimanual robotic manipulation.
A new model for simulating cloth manipulation in robots, accurate to within 1cm.
Robot learns to manipulate objects using multiple geometric representations.
Robotic clothing manipulation improved with fashion image analysis techniques.
Robotic grasping system learns to target objects from a single image.
Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only when the task has been successfully completed, can lead to better policies. Howe…
Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world ro…
We propose a tool-use model that can detect the features of tools, target objects, and actions from the provided effects of object manipulation. We construct a model that enables robots to manipulate objects with tools, using infant learning as a concept. To realize this, we train sensory-motor data recorded during a t…
This work tackles real-world robotic reinforcement learning challenges.
Robotic grasp stability improved with fingertip slippage detection.
CausalWorld benchmarks robotic manipulation tasks with causal structure for transfer learning.
Paper presents a method for efficient robot adaptation using fine-tuning.
HO2 learns options from data efficiently, improving robot manipulation tasks.
Human input has enabled autonomous systems to improve their capabilities and achieve complex behaviors that are otherwise challenging to generate automatically. Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives. These techniques assume that the huma…
In this paper, we study the problem of learning vision-based dynamic manipulation skills using a scalable reinforcement learning approach. We study this problem in the context of grasping, a longstanding challenge in robotic manipulation. In contrast to static learning behaviors that choose a grasp point and then execu…
Intelligent Object manipulation for grasping is a challenging problem for robots. Unlike robots, humans almost immediately know how to manipulate objects for grasping due to learning over the years. A grown woman can grasp objects more skilfully than a child because of learning skills developed over years, the absence …
Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. Traditional task and motion planning (TAMP) methods can solve complex tasks but require full state observability and are not adapted to dynamic scene changes. Recent learning methods can operate direct…
Survey examines challenges and solutions in sim-to-real transfer for robotics.
Robotic systems are ever more capable of automation and fulfilment of complex tasks, particularly with reliance on recent advances in intelligent systems, deep learning and artificial intelligence. However, as robots and humans come closer in their interactions, the matter of interpretability, or explainability of robo…
Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes. However, learning a model that captures the dynamics of complex skills represents a m…
KINet learns object interactions without supervision for robotic pushing.
Recognizing an object's material can inform a robot on the object's fragility or appropriate use. To estimate an object's material during manipulation, many prior works have explored the use of haptic sensing. In this paper, we explore a technique for robots to estimate the materials of objects using spectroscopy. We d…
We envision that in the near future, humanoid robots would share home space and assist us in our daily and routine activities through object manipulations. One of the fundamental technologies that need to be developed for robots is to enable them to detect objects and recognize them for effective manipulations and take…
Weak supervision enables learning causal representations from unstructured data.
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
Motion planning and control are key problems in a collection of robotic applications including the design of autonomous agile vehicles and of minimalist manipulators. These problems can be accurately formalized within the language of affine connections and of geometric control theory. In this paper we overview recent r…
Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to…
Tool manipulation is vital for facilitating robots to complete challenging task goals. It requires reasoning about the desired effect of the task and thus properly grasping and manipulating the tool to achieve the task. Task-agnostic grasping optimizes for grasp robustness while ignoring crucial task-specific constrain…
We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot. This is made possible by two key components: a novel algorithm, which we call automatic domain randomization (ADR) and a robot platform built for machine learning. ADR automatic…
ROBEL is an open-source platform of cost-effective robots designed for reinforcement learning in the real world. ROBEL introduces two robots, each aimed to accelerate reinforcement learning research in different task domains: D'Claw is a three-fingered hand robot that facilitates learning dexterous manipulation tasks, …
Real-life control tasks involve matters of various substances---rigid or soft bodies, liquid, gas---each with distinct physical behaviors. This poses challenges to traditional rigid-body physics engines. Particle-based simulators have been developed to model the dynamics of these complex scenes; however, relying on app…
Learning robot objective functions from human input has become increasingly important, but state-of-the-art techniques assume that the human's desired objective lies within the robot's hypothesis space. When this is not true, even methods that keep track of uncertainty over the objective fail because they reason about …
In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based fr…
This work learns visual representations for deformable objects using contrastive estimation.
The paper proposes a method to learn from both simulation and real-world data.
New method learns robot actions from videos without explicit labels.
ORIL learns a reward function from unlabeled data to improve robot learning.
A new framework for robot block-stacking tasks using causal probabilistic models.
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system like friction coefficients…
Vision and learning have made significant progress that could improve robotics policies for complex tasks and environments. Learning deep neural networks for image understanding, however, requires large amounts of domain-specific visual data. While collecting such data from real robots is possible, such an approach lim…
Robot learns to juggle two balls from 56 minutes of experience.