This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.
problem Challenges in working with real robotic hardware, especially position-controlled robots.
method Combines RL with traditional force control techniques, implementing parallel position/force control and admittance control.
result Validated methods on both simulation and real robot (UR3 e-series) for force control.
DIGIT is a low-cost tactile sensor for in-hand manipulation.
problem Difficulty in sensing contact forces limits robotic manipulation.
method DIGIT miniaturizes and improves a vision-based tactile sensor.
result DIGIT enables better control of interactions with the environment.
Diffusion models enhance robotic manipulation through probabilistic multi-modal learning.
problem Enhancing robotic manipulation through robust and multi-modal learning.
method Probabilistic diffusion models integrating imitation and reinforcement learning.
result Diffusion models improve grasp learning, trajectory planning, and data augmentation in robotics.
Robots learn to handle complex tasks creatively using DRL.
problem Robotic manipulation challenges and intelligence.
method Designing challenging manipulation tasks, applying DRL for robot training.
result Robots exhibit creative and non-intuitive problem-solving.
A new reward shaping method balances learning efficiency and effectiveness for robot manipulation.
problem Efficient and effective learning in robot manipulations with system uncertainty.
method Dense2Sparse reward shaping method combining dense and sparse rewards.
result Dense2Sparse method achieves higher expected reward and better system uncertainty tolerance.
Soft Q-learning improves sample efficiency in robotic manipulation.
problem Limited interaction time in real-world robotic tasks.
method Soft Q-learning for maximum entropy policies, with composability.
result Soft Q-learning policies are more sample efficient and can be composed.
A novel RL approach learns robotic manipulation without human demonstrations.
problem Learning robotic manipulation policies efficiently and effectively.
method Introducing simulated locomotion demonstration rewards (SLDRs) to enable RL learning.
result The approach achieves higher success rates and faster learning compared to alternatives.
Paper presents a new port-Hamiltonian model for vehicle manipulators.
problem Complex mechanical systems' energy flow and conservation.
method Derives port-Hamiltonian dynamics from Hamiltonian reduction theory.
result Establishes mathematical equivalence with existing formulations.
A new method for robot manipulation tasks using imagined object goals.
problem Learning robot manipulation in sparse reward environments.
method Train objects to reach target positions, then use predictions to create a curriculum of tasks.
result Higher success rates in challenging learning scenarios compared to alternatives.
Robot learns tool use from effects, detecting features of tools, objects, and actions.
problem Teaching robots to understand and manipulate objects using tools.
method Deep learning model trained on sensory-motor data from a robot performing a tool-use task.
result Robot can detect features of tools, objects, and actions from effects of object manipulation.
This work proposes a RL approach to learn versatile robotic manipulation tasks.
problem Challenging manipulation tasks in robotics and vision.
method Reinforcement learning (RL) to combine primitive skills, no intermediate rewards, few demonstrations, and efficient skill learning.
result Versatile robotic manipulation in challenging settings with temporary occlusions and dynamic scene changes.
Proposes KStar Diffuser for kinematics-aware bimanual robotic manipulation.
problem Challenges in applying imitation learning to bimanual robotic tasks.
method Integrates physical robot structure into action prediction using a dynamic spatial-temporal graph and differentiable kinematics.
result Effective generation of kinematics-aware actions in both simulation and real-world environments.
Hierarchical RL system for robotic manipulation with explainable decision-making.
problem Interpretability of robot decision-making for human operators.
method Dot-to-Dot: Hierarchical Deep Reinforcement Learning.
result Efficient learning of complex actions/states by low-level agent and interpretable high-level representation.
A new model for simulating cloth manipulation in robots, accurate to within 1cm.
problem Accurately simulating cloth manipulation in robots, especially in moderate stress environments.
method A continuous, isometric strain model for textiles, treating them as inextensible surfaces with only isometric motions. Aerodynamic effects are incorporated through virtual uncoupling of mass.
result Simulations are accurate to within 1cm compared to real-world manipulation, even with coarse meshes.
Robot learns to manipulate objects using multiple geometric representations.
problem Manipulation tasks are poorly represented by Cartesian coordinates.
method Extends Gaussian distributions on Riemannian manifolds to analyze demonstrations, formulating the problem as an optimal control problem.
result Robot can generalize manipulation tasks using multiple geometric representations.
Robotic clothing manipulation improved with fashion image analysis techniques.
problem Automated identification of clothing categories and landmarks for robotic tasks.
method Training data augmentation methods and rotation invariant convolutions.
result Our approach outperforms state-of-the-art models on unseen datasets.
Robotic grasping system learns to target objects from a single image.
problem Robotic grasping in unstructured environments.
method Distributed reinforcement learning, active vision, synchronous SGD.
result System learns to grasp unseen objects without retraining.
RL learns dexterous object reorientation on a physical robot.
problem Learning complex in-hand manipulation tasks on physical robots.
method Reinforcement learning in a simulated environment, transfer learning.
result RL policies transfer from simulation to physical robot.
QT-Opt learns dynamic grasping strategies for robots.
problem Learning dynamic grasping for robots in real-world settings.
method Scalable self-supervised vision-based reinforcement learning.
result 96% grasp success on unseen objects with real-world learning.
This work tackles real-world robotic reinforcement learning challenges.
problem Limited success of reinforcement learning in real-world robotics.
method Proposes a system for autonomous real-world learning without instrumentation.
result Demonstrates a complete system that learns without human intervention.
TOG-Net optimizes grasping for tool manipulation in simulated self-supervised learning.
problem Optimizing grasping for tool manipulation in robots.
method Simulated self-supervised learning with Task-Oriented Grasping Network (TOG-Net).
result Achieved 71.1% task success rate for sweeping and 80.0% for hammering.
Robotic grasp stability improved with fingertip slippage detection.
problem Improving grasp stability in robotic manipulation.
method Task-relevant feature extraction and efficient classifier design for fingertip slippage detection.
result The proposed method effectively detects object slippage with fingertips in an online fashion.
MaMiC proposes a dual curriculum for robot manipulation tasks with sparse rewards.
problem Overcoming exploratory constraints in robot manipulation tasks with sparse rewards.
method Includes a macro curriculum scheme and a micro curriculum scheme to guide learning.
result Combining macro and micro curriculum strategies improves performance in robot manipulation tasks.
CausalWorld benchmarks robotic manipulation tasks with causal structure for transfer learning.
problem Challenges in transferring learned skills to new robotic manipulation environments.
method Proposes a simulation-based benchmark with a combinatorial family of tasks.
result Demonstrates the feasibility of tasks in the benchmark and provides baseline results.
Robots detect and recognize objects in real-time for better manipulation.
problem Real-time object detection and recognition for humanoid robots.
method Modified YOLOv3 algorithm, quantization, and re-arrangement of layers for low-compute NAO robots.
result Robots can perform real-time detection, recognition, and localization of objects.
Paper presents a method for efficient robot adaptation using fine-tuning.
problem Continuous adaptation of robot learning systems in real-world scenarios.
method Fine-tuning previously learned policies using off-policy reinforcement learning.
result Fine-tuning leads to substantial performance gains and adaptation to new conditions.
HO2 learns options from data efficiently, improving robot manipulation tasks.
problem Learning options from raw pixel inputs in 3D robot manipulation tasks.
method HO2 infers likely option choices and trains all policy components off-policy.
result HO2 outperforms existing methods on 3D robot manipulation tasks.
Optimizes synthetic image augmentation for sim2real policy transfer in robotics.
problem Difficulty in transferring learned policies from simulated to real environments.
method Optimizes random transformations to augment synthetic images, enabling policy learning without real data.
result Significant improvement in policy accuracy on real robots for three manipulation tasks.
Paper addresses hypothesis space misspecification in learning from human demonstrations and corrections.
problem Hypothesis space misspecification in learning from human demonstrations and corrections.
method Reason explicitly about how well the robot can explain human inputs given its hypothesis space.
result Demonstrates method on a 7 DOF robot manipulator.
Robotic grasping improved using evolutionary computing and deep reinforcement learning.
problem Developing a robot capable of grasping objects as skillfully as humans.
method Position estimation using Genetic Algorithm and regression, orientation learning using deep reinforcement learning.
result Deep reinforcement learning model outperforms traditional methods for orientation learning.
Paper learns particle dynamics for versatile object manipulation.
problem Challenges in traditional rigid-body physics engines for complex scenes.
method Combines learning with particle-based systems for versatile object manipulation.
result Robots achieve complex manipulation tasks using the learned simulator.
Robot learns from human actions to perform complex tasks.
problem Learning complex skills from interaction data with embodiment differences.
method Formulated graphical model, treated action as observed variable, used domain-dependent prior.
result Robotic planning agent can learn tool use from human observations.
Robotic arm learns to manipulate a ball by choosing goals from learned experience.
problem Efficient discovery of skills for long-living autonomous agents without supervision.
method Intrinsically motivated goal exploration using learned goal spaces from deep representation learning.
result Recent results show applicability of learned goal spaces on real-world robotic tasks.
Survey examines challenges and solutions in sim-to-real transfer for robotics.
problem Challenges in transferring robotic systems from simulation to real-world environments.
method Leveraging techniques like domain randomization, real-to-sim transfer, state and action abstractions, and sim-real co-training.
result Promising results in closing the reality gap across various robotic domains.
Robots can classify household materials using spectroscopy.
problem Estimating the material of household objects during manipulation.
method Used spectroscopy to estimate material classification of 50 flat objects.
result Achieved 94.6% material classification accuracy with one spectral sample per object.
KINet learns object interactions without supervision for robotic pushing.
problem Lack of supervised data for object-centric forward prediction.
method End-to-end unsupervised framework using keypoint representation and contrastive estimation.
result Automatically generalizes to unseen scenarios and accurately predicts future states.
ANNs solve complex inverse kinematics of a Tricept parallel robot.
problem Solving inverse kinematics for a Tricept parallel robot.
method Developed kinematic equations, used ANNs (MLP and RBF) for solving.
result ANNs provided proper accuracy and speed in solving complex inverse kinematics.
HGG generates goals to improve sample efficiency in robotic tasks.
problem Efficiency in reinforcement learning with sparse reward signals.
method Generates valuable hindsight goals for reinforcement learning.
result Significantly improved sample efficiency over HER.
This paper prioritizes experience replay in robotics using energy-based principles.
problem Randomly replaying experience in HER leads to inefficient learning.
method Developed an energy-based framework to prioritize hindsight experience in robotic manipulation tasks.
result EBP outperforms state-of-the-art approaches in robotic manipulation tasks.
Proposes a method to boost deep reinforcement learning with sparse rewards.
problem Challenges in learning complex behaviors with long horizons and sparse rewards.
method Predictive coding for reward shaping.
result Achieves better learning by providing reward signals that understand environment dynamics and emphasize useful features.
SAC-X enables learning complex behaviors from sparse rewards.
problem Learning complex behaviors from sparse reward signals.
method Scheduled Auxiliary Control (SAC-X) with auxiliary tasks.
result SAC-X enables efficient exploration and complex behavior learning.
Agent learns third-person manipulation tasks from a single video.
problem Learning from third-person videos to perform novel tasks.
method Decoupling high-level task generation from low-level action prediction.
result Agent successfully learns and performs tasks in unseen scenarios.
Weak supervision enables learning causal representations from unstructured data.
problem Learning high-level causal representations from unstructured data like images.
method Weakly supervised setting with paired samples before and after interventions. Implicit latent causal models using variational autoencoders.
result Models can reliably identify causal structure and disentangle causal variables.
Time-agnostic predictors predict frames without fixed time intervals.
problem Predicting events in the future or between waypoints is difficult.
method Decouple visual prediction from a rigid notion of time, discovering predictable 'bottleneck' frames.
result Predictions are of higher visual quality and correspond to coherent semantic subgoals.
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.
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…
Robot solves Rubik's cube using simulation-trained models.
problem Solving Rubik's cube with a robot hand.
method Automatic domain randomization (ADR) and a custom robot platform.
result Control policies and vision state estimators trained with ADR exhibit improved sim2real transfer.
ROBEL platform accelerates reinforcement learning with low-cost robots.
problem Accelerating reinforcement learning research in robotics.
method Open-source platform of cost-effective robots for real-world reinforcement learning.
result Robots D'Claw and D'Kitty facilitate learning dexterous manipulation and agile locomotion tasks.