A new Q-learning controller improves line follower robot control.
problem Challenges in controlling line follower robots due to unknown mechanical characteristics and uncertainties.
method Simulated annealing based Q learning method to address controller performance issues.
result The proposed controller outperforms conventional P controllers in line follower robots.
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.
Controller stabilizes spherical robot's position and line-of-sight.
problem Stabilizing a spherical robot's position and line-of-sight.
method Geometric control law with feedforward and proportional-derivative control.
result Controller performance validated through simulations.
Automates decision-making for human operators managing multiple robots.
problem Limited human operator attention when controlling multiple robots.
method Learned model of user preferences from easy settings to automatically identify the most critical robot.
result Automated decision-making can assist human operators in managing more robots than their attention allows.
Paper proposes a method to control robots of different shapes efficiently.
problem Learning optimal control policies for robots of various shapes is challenging.
method Hierarchical architecture with hypernetworks and fixed attention mechanism.
result Method improves learning performance and generalizes to unseen morphologies.
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.
This research evaluates learning models for bionic robots, focusing on transfer function identification.
problem Developers need guidance on selecting and constructing transfer functions for bionic robots.
method Comprehensive evaluation strategy including data collection, learning model selection, comparative analysis, and transfer function identification.
result A framework for effectively dealing with multi-input multi-output robotic data.
A decentralized deep RL controller improves hexapod locomotion learning.
problem Deep RL struggles with real-world legged robot control.
method Decentralized deep RL on a hexapod robot.
result Decentralized approach learns better and faster.
Robotics: Rolling robots on a moving platform can be controlled.
problem Controlling the motion of rolling robots atop a moving platform.
method Developed a mathematical model and demonstrated simulations.
result Platform acceleration can control robot's heading and motion.
Robustified controllers reduce fine-tuning time for sim-to-real transfer learning.
problem Reducing fine-tuning time for sim-to-real transfer learning of complex robotic tasks.
method Learn robustified controllers in simulation by changing parameters for successive episodes.
result Fine-tuning time is substantially reduced for robustified controllers.
RL controls small soccer robots in a real league, beating human-designed policies.
problem Training robots to play complex, real-world sports.
method Sim-to-Real RL approach, training in simulated environment, applying to real-world robots.
result Robots learned policies to compete effectively, beating human-designed strategies.
Neural circuit model re-purposed for robotic control tasks.
problem Learning simple robotic control tasks.
method Re-purposing a biological neural circuit model to control robotic tasks using a search-based optimization algorithm.
result Neuronal Circuit Policies (NCPs) perform on par and in some cases surpass contemporary deep learning models with fewer parameters and interpretable dynamics.
Robot learns to dress people safely using deep learning.
problem Robots lack common sense about physical interactions with clothing.
method Deep recurrent model predicts garment forces, used with MPC.
result Robot can better assist in dressing without high forces.
Method trains vision and control policies on real robots quickly.
problem Training vision-based control policies on real robots efficiently.
method Multi-task Reinforcement Learning with auxiliary tasks.
result Significant learning speed-ups and task learning from-scratch.
Hybrid method uses GP models to control robot trajectories.
problem Minimizing unmodeled dynamics in robot motion.
method Embeds non-parametric statistical models (GPs) for feedback control.
result Proposed method avoids complex analysis for wide trajectory classes.
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.
Multi-task learning improves robotic control in continuous action spaces.
problem Robotic control in continuous action spaces lacks effective multi-task learning methods.
method Applied multi-task learning methods to continuous action spaces and compared performance with baselines.
result Multi-task learning outperforms baselines and alternative methods in continuous control tasks.
A new reinforcement learning method for robots thinking and moving simultaneously.
problem Concurrent control in robotic systems where actions must be decided while the system is still evolving.
method Continuous-time Bellman equations, discretization aware of system delays, and architectural extension to deep reinforcement learning.
result The method successfully handles tasks requiring simultaneous decision-making and action execution.
New sensor placement affects robot controller learnability.
problem Catastrophic forgetting in neural controllers for robots.
method Demonstrated how sensor placement alters loss function manifolds.
result Sensor placement can reduce or induce catastrophic forgetting.
DeepWeeds dataset aids in robust weed species classification for rangeland robotics.
problem Robust classification of weed species in rangeland environments.
method Development of a large multiclass image dataset and application of deep learning models.
result Inception-v3 and ResNet-50 achieved 95.1% and 95.7% classification accuracy, respectively.
Novel approach for sim-to-real transfer using MPC and task representations.
problem Difficulty of sim-to-real transfer systems producing generalizable policies.
method Model-predictive control (MPC) and task representation learning.
result Direct transfer of multi-skill policy to real robot for unseen 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…
Paper learns robot's end-effector position without prior info.
problem Lack of prior robot structure or sensor info.
method Generates internal end-effector config from raw data.
result Can control robot without prior kinematic info.
Study aims to develop a humanoid robot dialogue system.
problem Current dialogue systems lack attention to non-verbal cues.
method Participated in a competition to develop a system with facial expressions and gaze control.
result Developed a humanoid robot dialogue system.
Robot learns to control itself without rewards.
problem Autonomous reinforcement learning without access to rewards.
method Distributional planning networks optimizing for an embedding space.
result Learned goal metrics enable autonomous reinforcement learning.
A novel controller for wheeled robots handles joystick inputs for smooth steering.
problem Steering control for differential-drive wheeled robots from indirect joystick inputs.
method Developed a geometric controller based on Darboux frame kinematics.
result Smooth trajectories achieved with safety constraints and no desired states.
Deep RL trains a robust humanoid push-recovery policy.
problem Training robust humanoid push-recovery policies.
method Model-free Deep Reinforcement Learning.
result Policy learns robust behaviors across the entire body.
The paper addresses optimal control on Riemannian manifolds, introducing biased splines for robotic systems.
problem Optimal control on Riemannian manifolds with a mathematically natural cometric not capturing true motion cost.
method Encoding torque-based actuators into a cometric, characterizing optimal solutions via a 4th order differential equation.
result Identified a tensor as the geometric source of biasing solutions away from ordinary splines and geodesics.
We construct a privileged system of coordinates with respect to the controlling distribution of a trident snake robot and, furthermore, we construct a nilpotent approximation with respect to the given filtration. Note that all constructions are local in the neighbourhood of a particular point. We compare the motions co…
Action chunking and data exploration improve behavior cloning in robotics.
problem Exponential errors in learning from demonstrations for continuous control tasks.
method Action chunking and exploratory data collection.
result Control-theoretic stability is key to improving imitation learning.
Robots learn to navigate rough terrain using reinforcement learning.
problem Generalizing robot behavior to new, unseen rough terrains.
method PPMC RL Training Algorithm
result Robots achieve 100% success rate in learning new rough terrain maps.
This work evaluates task-agnostic exploration methods for fixed-batch learning.
problem Expensive real-world experience for robotics tasks.
method Fixed datasets for arbitrary task learning.
result Improved offline learning for robotics tasks.
TIDBD adapts step sizes online for better robotic predictions.
problem Choosing appropriate learning parameters for online prediction-learning.
method Temporal-Difference Incremental Delta-Bar-Delta (TIDBD) for step-size adaptation.
result TIDBD performs comparably to classic TD learning and detects sensor failures.
Paper proposes a new method to optimize robot body structure and control policy.
problem Optimizing robot body structure and control policy in a coupled manner.
method Revisits co-design problem as a Stackelberg game, incorporating control adaptation dynamics.
result Stackelberg PPO outperforms standard PPO in stability and performance.
Paper provides closed-form time derivatives for rigid body systems.
problem Need for time derivatives of equations of motion in robotics.
method Lie group formulation for rigid body systems to derive closed-form derivatives up to second-order.
result Closed-form equations provide direct insight into system dynamics.
Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system t…
A new RL framework handles autocorrelated actions for better learning and stability.
problem Improving reinforcement learning algorithms for better stability and efficiency.
method Introduces a new algorithm that optimizes policies with autocorrelated actions.
result The new algorithm outperforms existing methods in four simulated control problems.
Paper learns versatile balancing and recovery motions for humanoid robots.
problem Training humanoid robots to handle unexpected perturbations.
method Hierarchical Deep Reinforcement Learning in a physics simulator.
result Learned skills comparable to preprogrammed controllers but more adaptable.
This paper improves robot grasping by integrating meta-control and latent-space imagination.
problem Dual-system approaches fail to consider the reliability of the learned model when making multiple-step predictions.
method A meta-controller arbitrates between model-based and model-free decisions based on local reliability, encouraging actions that improve the model and generating imagined experiences for additional training.
result Our approach learns near-optimal grasping policies in dense- and sparse-reward environments, outperforming baseline and state-of-the-art methods.
New method transfers robotic control policies to unknown environments using a family of policies.
problem Transfer of robotic control policies trained in simulation to real hardware is difficult due to environment differences.
method Simultaneously learns a family of policies with different behaviors; searches for the best policy based on task performance.
result Demonstrates superior performance in unknown environments compared to other methods, overcoming larger modeling errors.
This work uses QPGPs to improve ILC performance in repetitive tasks.
problem Performance degradation in repetitive motion tasks due to environmental changes and robot wear.
method Incorporates Quasi-Periodic Gaussian Processes into a predictive ILC framework.
result The proposed approach achieves faster convergence and robustness under disturbances.
MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.
problem Optimizing risk in reinforcement learning control problems.
method Mean-Variance Policy Iteration (MVPI) framework for risk-averse control in MDPs.
result Risk-averse TD3 outperforms previous methods in robot simulation tasks.
Deep RL controls robotic arms efficiently.
problem Continuous control of robotic arms.
method Combination of two reinforcement learning methods and preprocessing techniques.
result The new combination learns more effectively than a baseline.
Robotic table tennis learns efficient policies to return balls at 100Hz.
problem Developing efficient robotic table tennis strategies.
method Model-free reinforcement learning using evolutionary search on CNN-based policies.
result Robots can develop multi-modal styles (forehand and backhand) with 80% return rate.
Toolbox provides datasets and metrics for state representation learning.
problem Lack of standard evaluation datasets, metrics and tasks for state representation learning.
method Provides a set of environments, data generators, robotic control tasks, metrics and tools.
result Facilitates iterative state representation learning and evaluation in reinforcement learning settings.
Data-driven control of robotic systems using Koopman operators with error bounds.
problem Real-time control of nonlinear robotic systems with unknown dynamics.
method Constructing a Koopman operator-based linear representation using higher-order derivatives of nonlinear dynamics, with error bounds derived from Taylor series accuracy analysis.
result The Koopman model provides marginally better performance than competing nonlinear modeling methods and can be efficiently controlled using linear control design tools.
Proposes hybrid reinforcement learning for both discrete and continuous control problems.
problem Real-world control problems involving both discrete and continuous decision variables.
method Solves hybrid problems by optimizing for discrete and continuous actions simultaneously.
result Efficiently solves hybrid reinforcement learning problems and improves upon expert heuristics.
The paper studies how neural policies can be interpreted using decision trees.
problem Understanding how machine learning controllers make decisions in complex environments.
method The approach involves disentangled representation using decision trees to interpret neural policies.
result The paper shows that disentanglement of learned neural dynamics improves interpretability.