Zhibin Li

Kai Yuan, Noor Sajid, Karl Friston et al.

Humans can produce complex whole-body motions when interacting with their surroundings, by planning, executing and combining individual limb movements. We investigated this fundamental aspect of motor control in the setting of autonomous robotic operations. We approach this problem by hierarchical generative modelling equipped with multi-level planning-for autonomous task completion-that mimics the deep temporal architecture of human motor control. Here, temporal depth refers to the nested time scales at which successive levels of a forward or generative model unfold, for example, delivering an object requires a global plan to contextualise the fast coordination of multiple local movements of limbs. This separation of temporal scales also motivates robotics and control. Specifically, to achieve versatile sensorimotor control, it is advantageous to hierarchically structure the planning and low-level motor control of individual limbs. We use numerical and physical simulation to conduct experiments and to establish the efficacy of this formulation. Using a hierarchical generative model, we show how a humanoid robot can autonomously complete a complex task that necessitates a holistic use of locomotion, manipulation, and grasping. Specifically, we demonstrate the ability of a humanoid robot that can retrieve and transport a box, open and walk through a door to reach the destination, approach and kick a football, while showing robust performance in presence of body damage and ground irregularities. Our findings demonstrated the effectiveness of using human-inspired motor control algorithms, and our method provides a viable hierarchical architecture for the autonomous completion of challenging goal-directed tasks.

Tiantian He, Zhibin Li, Yongshun Gong et al.

Non-linear activation functions, e.g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs). Due to the complex non-linear characteristic of samples, the objective of those activation functions is to project samples from their original feature space to a linear separable feature space. This phenomenon ignites our interest in exploring whether all features need to be transformed by all non-linear functions in current typical NNs, i.e., whether there exists a part of features arriving at the linear separable feature space in the intermediate layers, that does not require further non-linear variation but an affine transformation instead. To validate the above hypothesis, we explore the problem of linear feature disentanglement for neural networks in this paper. Specifically, we devise a learnable mask module to distinguish between linear and non-linear features. Through our designed experiments we found that some features reach the linearly separable space earlier than the others and can be detached partly from the NNs. The explored method also provides a readily feasible pruning strategy which barely affects the performance of the original model. We conduct our experiments on four datasets and present promising results.

Nathan Herr, Fernando Acero, Roberta Raileanu et al.

Large Language Models (LLMs) have been increasingly used in real-world settings, yet their strategic decision-making abilities remain largely unexplored. To fully benefit from the potential of LLMs, it's essential to understand their ability to function in complex social scenarios. Game theory, which is already used to understand real-world interactions, provides a good framework for assessing these abilities. This work investigates the performance and merits of LLMs in canonical game-theoretic two-player non-zero-sum games, Stag Hunt and Prisoner Dilemma. Our structured evaluation of GPT-3.5, GPT-4-Turbo, GPT-4o, and Llama-3-8B shows that these models, when making decisions in these games, are affected by at least one of the following systematic biases: positional bias, payoff bias, or behavioural bias. This indicates that LLMs do not fully rely on logical reasoning when making these strategic decisions. As a result, it was found that the LLMs' performance drops when the game configuration is misaligned with the affecting biases. When misaligned, GPT-3.5, GPT-4-Turbo, GPT-4o, and Llama-3-8B show an average performance drop of 32\%, 25\%, 34\%, and 29\% respectively in Stag Hunt, and 28\%, 16\%, 34\%, and 24\% respectively in Prisoner's Dilemma. Surprisingly, GPT-4o (a top-performing LLM across standard benchmarks) suffers the most substantial performance drop, suggesting that newer models are not addressing these issues. Interestingly, we found that a commonly used method of improving the reasoning capabilities of LLMs, chain-of-thought (CoT) prompting, reduces the biases in GPT-3.5, GPT-4o, and Llama-3-8B but increases the effect of the bias in GPT-4-Turbo, indicating that CoT alone cannot fully serve as a robust solution to this problem. We perform several additional experiments, which provide further insight into these observed behaviours.

Daniel C. H. Tan, Fernando Acero, Robert McCarthy et al.

Guaranteeing safe behaviour of reinforcement learning (RL) policies poses significant challenges for safety-critical applications, despite RL's generality and scalability. To address this, we propose a new approach to apply verification methods from control theory to learned value functions. By analyzing task structures for safety preservation, we formalize original theorems that establish links between value functions and control barrier functions. Further, we propose novel metrics for verifying value functions in safe control tasks and practical implementation details to improve learning. Our work presents a novel method for certificate learning, which unlocks a diversity of verification techniques from control theory for RL policies, and marks a significant step towards a formal framework for the general, scalable, and verifiable design of RL-based control systems. Code and videos are available at this https url: https://rl-cbf.github.io/

Eleftherios Triantafyllidis, Filippos Christianos, Zhibin Li

Current reinforcement learning algorithms struggle in sparse and complex environments, most notably in long-horizon manipulation tasks entailing a plethora of different sequences. In this work, we propose the Intrinsically Guided Exploration from Large Language Models (IGE-LLMs) framework. By leveraging LLMs as an assistive intrinsic reward, IGE-LLMs guides the exploratory process in reinforcement learning to address intricate long-horizon with sparse rewards robotic manipulation tasks. We evaluate our framework and related intrinsic learning methods in an environment challenged with exploration, and a complex robotic manipulation task challenged by both exploration and long-horizons. Results show IGE-LLMs (i) exhibit notably higher performance over related intrinsic methods and the direct use of LLMs in decision-making, (ii) can be combined and complement existing learning methods highlighting its modularity, (iii) are fairly insensitive to different intrinsic scaling parameters, and (iv) maintain robustness against increased levels of uncertainty and horizons.

Eleftherios Triantafyllidis, Fernando Acero, Zhaocheng Liu et al.

Solving long sequential tasks poses a significant challenge in embodied artificial intelligence. Enabling a robotic system to perform diverse sequential tasks with a broad range of manipulation skills is an active area of research. In this work, we present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN), to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation. ROMAN achieves task versatility and robust failure recovery by integrating behavioural cloning, imitation learning, and reinforcement learning. It consists of a central manipulation network that coordinates an ensemble of various neural networks, each specialising in distinct re-combinable sub-tasks to generate their correct in-sequence actions for solving complex long-horizon manipulation tasks. Experimental results show that by orchestrating and activating these specialised manipulation experts, ROMAN generates correct sequential activations for accomplishing long sequences of sophisticated manipulation tasks and achieving adaptive behaviours beyond demonstrations, while exhibiting robustness to various sensory noises. These results demonstrate the significance and versatility of ROMAN's dynamic adaptability featuring autonomous failure recovery capabilities, and highlight its potential for various autonomous manipulation tasks that demand adaptive motor skills.

Robert McCarthy, Daniel C. H. Tan, Dominik Schmidt et al.

Scaling deep learning to massive and diverse internet data has driven remarkable breakthroughs in domains such as video generation and natural language processing. Robot learning, however, has thus far failed to replicate this success and remains constrained by a scarcity of available data. Learning from videos (LfV) methods aim to address this data bottleneck by augmenting traditional robot data with large-scale internet video. This video data provides foundational information regarding physical dynamics, behaviours, and tasks, and can be highly informative for general-purpose robots. This survey systematically examines the emerging field of LfV. We first outline essential concepts, including detailing fundamental LfV challenges such as distribution shift and missing action labels in video data. Next, we comprehensively review current methods for extracting knowledge from large-scale internet video, overcoming LfV challenges, and improving robot learning through video-informed training. The survey concludes with a critical discussion of future opportunities. Here, we emphasize the need for scalable foundation model approaches that can leverage the full range of available internet video and enhance the learning of robot policies and dynamics models. Overall, the survey aims to inform and catalyse future LfV research, driving progress towards general-purpose robots.

Matthew Lai, Keegan Go, Zhibin Li et al.

Modern robotic manufacturing requires collision-free coordination of multiple robots to complete numerous tasks in shared, obstacle-rich workspaces. Although individual tasks may be simple in isolation, automated joint task allocation, scheduling, and motion planning under spatio-temporal constraints remain computationally intractable for classical methods at real-world scales. Existing multi-arm systems deployed in the industry rely on human intuition and experience to design feasible trajectories manually in a labor-intensive process. To address this challenge, we propose a reinforcement learning (RL) framework to achieve automated task and motion planning, tested in an obstacle-rich environment with eight robots performing 40 reaching tasks in a shared workspace, where any robot can perform any task in any order. Our approach builds on a graph neural network (GNN) policy trained via RL on procedurally-generated environments with diverse obstacle layouts, robot configurations, and task distributions. It employs a graph representation of scenes and a graph policy neural network trained through reinforcement learning to generate trajectories of multiple robots, jointly solving the sub-problems of task allocation, scheduling, and motion planning. Trained on large randomly generated task sets in simulation, our policy generalizes zero-shot to unseen settings with varying robot placements, obstacle geometries, and task poses. We further demonstrate that the high-speed capability of our solution enables its use in workcell layout optimization, improving solution times. The speed and scalability of our planner also open the door to new capabilities such as fault-tolerant planning and online perception-based re-planning, where rapid adaptation to dynamic task sets is required.

Wenbin Hu, Fernando Acero, Eleftherios Triantafyllidis et al.

We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects, a task that requires fast, reactive, and accurately-timed robot motions. Our framework consists of five core modules: (i) an object state estimator that learns object trajectory prediction, (ii) a catching pose quality network that learns to score and rank object poses for catching, (iii) a reaching control policy trained to move the robot hand to pre-catch poses, (iv) a grasping control policy trained to perform soft catching motions for safe and robust grasping, and (v) a gating network trained to synthesize the actions given by the reaching and grasping policy. The former two modules are trained via supervised learning and the latter three use deep reinforcement learning in a simulated environment. We conduct extensive evaluations of our framework in simulation for each module and the integrated system, to demonstrate high success rates of in-flight catching and robustness to perturbations and sensory noise. Whilst only simple cylindrical and spherical objects are used for training, the integrated system shows successful generalization to a variety of household objects that are not used in training.

Fernando Acero, Zhibin Li

Recent advancements in reinforcement learning (RL) have led to remarkable achievements in robot locomotion capabilities. However, the complexity and ``black-box'' nature of neural network-based RL policies hinder their interpretability and broader acceptance, particularly in applications demanding high levels of safety and reliability. This paper introduces a novel approach to distill neural RL policies into more interpretable forms using Gradient Boosting Machines (GBMs), Explainable Boosting Machines (EBMs) and Symbolic Regression. By leveraging the inherent interpretability of generalized additive models, decision trees, and analytical expressions, we transform opaque neural network policies into more transparent ``glass-box'' models. We train expert neural network policies using RL and subsequently distill them into (i) GBMs, (ii) EBMs, and (iii) symbolic policies. To address the inherent distribution shift challenge of behavioral cloning, we propose to use the Dataset Aggregation (DAgger) algorithm with a curriculum of episode-dependent alternation of actions between expert and distilled policies, to enable efficient distillation of feedback control policies. We evaluate our approach on various robot locomotion gaits -- walking, trotting, bounding, and pacing -- and study the importance of different observations in joint actions for distilled policies using various methods. We train neural expert policies for 205 hours of simulated experience and distill interpretable policies with only 10 minutes of simulated interaction for each gait using the proposed method.

Chong Zhang, Wanming Yu, Zhibin Li

For model-free deep reinforcement learning of quadruped locomotion, the initialization of robot configurations is crucial for data efficiency and robustness. This work focuses on algorithmic improvements of data efficiency and robustness simultaneously through automatic discovery of initial states, which is achieved by our proposed K-Access algorithm based on accessibility metrics. Specifically, we formulated accessibility metrics to measure the difficulty of transitions between two arbitrary states, and proposed a novel K-Access algorithm for state-space clustering that automatically discovers the centroids of the static-pose clusters based on the accessibility metrics. By using the discovered centroidal static poses as the initial states, we can improve data efficiency by reducing redundant explorations, and enhance the robustness by more effective explorations from the centroids to sampled poses. Focusing on fall recovery as a very hard set of locomotion skills, we validated our method extensively using an 8-DoF quadrupedal robot Bittle. Compared to the baselines, the learning curve of our method converges much faster, requiring only 60% of training episodes. With our method, the robot can successfully recover to standing poses within 3 seconds in 99.4% of the test cases. Moreover, the method can generalize to other difficult skills successfully, such as backflipping.

Carlo Tiseo, Quentin Rouxel, Zhibin Li et al.

Robust dynamic interactions are required to move robots in daily environments alongside humans. Optimisation and learning methods have been used to mimic and reproduce human movements. However, they are often not robust and their generalisation is limited. This work proposed a hierarchical control architecture for robot manipulators and provided capabilities of reproducing human-like motions during unknown interaction dynamics. Our results show that the reproduced end-effector trajectories can preserve the main characteristics of the initial human motion recorded via a motion capture system, and are robust against external perturbations. The data indicate that some detailed movements are hard to reproduce due to the physical limits of the hardware that cannot reach the same velocity recorded in human movements. Nevertheless, these technical problems can be addressed by using better hardware and our proposed algorithms can still be applied to produce imitated motions.

Zhaocheng Liu, Fernando Acero, Zhibin Li

Legged robots are becoming increasingly powerful and popular in recent years for their potential to bring the mobility of autonomous agents to the next level. This work presents a deep reinforcement learning approach that learns a robust Lidar-based perceptual locomotion policy in a partially observable environment using Proximal Policy Optimisation. Visual perception is critical to actively overcome challenging terrains, and to do so, we propose a novel learning strategy: Dynamic Reward Strategy (DRS), which serves as effective heuristics to learn a versatile gait using a neural network architecture without the need to access the history data. Moreover, in a modified version of the OpenAI gym environment, the proposed work is evaluated with scores over 90% success rate in all tested challenging terrains.

Jiacheng Gu, Zhibin Li

This work proposed an efficient learning-based framework to learn feedback control policies from human teleoperated demonstrations, which achieved obstacle negotiation, staircase traversal, slipping control and parcel delivery for a tracked robot. Due to uncertainties in real-world scenarios, eg obstacle and slippage, closed-loop feedback control plays an important role in improving robustness and resilience, but the control laws are difficult to program manually for achieving autonomous behaviours. We formulated an architecture based on a long-short-term-memory (LSTM) neural network, which effectively learn reactive control policies from human demonstrations. Using datasets from a few real demonstrations, our algorithm can directly learn successful policies, including obstacle-negotiation, stair-climbing and delivery, fall recovery and corrective control of slippage. We proposed decomposition of complex robot actions to reduce the difficulty of learning the long-term dependencies. Furthermore, we proposed a method to efficiently handle non-optimal demos and to learn new skills, since collecting enough demonstration can be time-consuming and sometimes very difficult on a real robotic system.

Eleftherios Triantafyllidis, Wenbin Hu, Christopher McGreavy et al.

Assessing the performance of human movements during teleoperation and virtual reality is a challenging problem, particularly in 3D space due to complex spatial settings. Despite the presence of a multitude of metrics, a compelling standardized 3D metric is yet missing, aggravating inter-study comparability between different studies. Hence, evaluating human performance in virtual environments is a long-standing research goal, and a performance metric that combines two or more metrics under one formulation remains largely unexplored, particularly in higher dimensions. The absence of such a metric is primarily attributed to the discrepancies between pointing and manipulation, the complex spatial variables in 3D, and the combination of translational and rotational movements altogether. In this work, four experiments were designed and conducted with progressively higher spatial complexity to study and compare existing metrics thoroughly. The research goal was to quantify the difficulty of these 3D tasks and model human performance sufficiently in full 3D peripersonal space. Consequently, a new model extension has been proposed and its applicability has been validated across all the experimental results, showing improved modelling and representation of human performance in combined movements of 3D object pointing and manipulation tasks than existing work. Lastly, the implications on 3D interaction, teleoperation and object task design in virtual reality are discussed.

Christopher McGreavy, Zhibin Li

In legged locomotion, the relationship between different gait behaviors and energy consumption must consider the full-body dynamics and the robot control as a whole, which cannot be captured by simple models. This work studies the robot dynamics and whole-body optimal control as a coupled system to investigate energy consumption during balance recovery. We developed a 2-phase nonlinear optimization pipeline for dynamic stepping, which generates reachability maps showing complex energy-stepping relations. We optimize gait parameters to search all reachable locations and quantify the energy cost during dynamic transitions, which allows studying the relationship between energy consumption and stepping locations given different initial conditions. We found that to achieve efficient actuation, the stepping location and timing can have simple approximations close to the underlying optimality. Despite the complexity of this nonlinear process, we show that near-minimal effort stepping locations fall within a region of attractions, rather than a narrow solution space suggested by a simple model. This provides new insights into the non-uniqueness of near-optimal solutions in robot motion planning and control, and the diversity of stepping behavior in humans.

Eleftherios Triantafyllidis, Zhibin Li

Assessing human performance in robotic scenarios such as those seen in telepresence and teleoperation has always been a challenging task. With the recent spike in mixed reality technologies and the subsequent focus by researchers, new pathways have opened in elucidating human perception and maximising overall immersion. Yet with the multitude of different assessment methods in evaluating operator performance in virtual environments within the field of HCI and HRI, inter-study comparability and transferability are limited. In this short paper, we present a brief overview of existing methods in assessing operator performance including subjective and objective approaches while also attempting to capture future technical challenges and frontiers. The ultimate goal is to assist and pinpoint readers towards potentially important directions with the future hope of providing a unified immersion framework for teleoperation and telepresence by standardizing a set of guidelines and evaluation methods.

Iordanis Chatzinikolaidis, Zhibin Li

This paper presents a novel approach using sensitivity analysis for generalizing Differential Dynamic Programming (DDP) to systems characterized by implicit dynamics, such as those modelled via inverse dynamics and variational or implicit integrators. It leads to a more general formulation of DDP, enabling for example the use of the faster recursive Newton-Euler inverse dynamics. We leverage the implicit formulation for precise and exact contact modelling in DDP, where we focus on two contributions: (1) Contact dynamics in acceleration level that enables high-order integration schemes; (2) Formulation using an invertible contact model in the forward pass and a closed form solution in the backward pass to improve the numerical resolution of contacts. The performance of the proposed framework is validated (1) by comparing implicit versus explicit DDP for the swing-up of a double pendulum, and (2) by planning motions for two tasks using a single leg model making multi-body contacts with the environment: standing up from ground, where a priori contact enumeration is challenging, and maintaining balance under an external perturbation.

Timothée Anne, Jack Wilkinson, Zhibin Li

This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of actions of estimated the state-action trajectories, and then applies the optimal actions to maximize the reward. To achieve online model adaptation, our proposed method learns different latent vectors of each training condition, which are selected online given the newly collected data. Our work designs appropriate state space and reward functions, and optimizes feasible actions in an MPC fashion which are then sampled directly in the joint space considering constraints, hence requiring no prior design of specific walking gaits. We further demonstrate the robot's capability of detecting unexpected changes during interaction and adapting control policies quickly. The extensive validation on the SpotMicro robot in a physics simulation shows adaptive and robust locomotion skills under varying ground friction, external pushes, and different robot models including hardware faults and changes.

Mohammadreza Kasaei, Miguel Abreu, Nuno Lau et al.

This work aims to combine machine learning and control approaches for legged robots, and developed a hybrid framework to achieve new capabilities of balancing against external perturbations. The framework embeds a kernel which is a fully parametric closed-loop gait generator based on analytical control. On top of that, a neural network with symmetric partial data augmentation learns to automatically adjust the parameters for the gait kernel and to generate compensatory actions for all joints as the residual dynamics, thus significantly augmenting the stability under unexpected perturbations. The performance of the proposed framework was evaluated across a set of challenging simulated scenarios. The results showed considerable improvements compared to the baseline in recovering from large external forces. Moreover, the produced behaviours are more natural, human-like and robust against noisy sensing.

Zhicheng Wang, Anqiao Li, Yixiao Zheng et al.

Bounding is one of the important gaits in quadrupedal locomotion for negotiating obstacles. The authors proposed an effective approach that can learn robust bounding gaits more efficiently despite its large variation in dynamic body movements. The authors first pretrained the neural network (NN) based on data from a robot operated by conventional model based controllers, and then further optimised the pretrained NN via deep reinforcement learning (DRL). In particular, the authors designed a reward function considering contact points and phases to enforce the gait symmetry and periodicity, which improved the bounding performance. The NN based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully. A variety of environments are presented both indoors and outdoors with the authors approach. The authors approach shows efficient computing and good locomotion results by the Jueying Mini quadrupedal robot bounding over uneven terrain.

Iordanis Chatzinikolaidis, Yangwei You, Zhibin Li

This paper presents a novel contact-implicit trajectory optimization method using an analytically solvable contact model to enable planning of interactions with hard, soft, and slippery environments. Specifically, we propose a novel contact model that can be computed in closed-form, satisfies friction cone constraints and can be embedded into direct trajectory optimization frameworks without complementarity constraints. The closed-form solution decouples the computation of the contact forces from other actuation forces and this property is used to formulate a minimal direct optimization problem expressed with configuration variables only. Our simulation study demonstrates the advantages over the rigid contact model and a trajectory optimization approach based on complementarity constraints. The proposed model enables physics-based optimization for a wide range of interactions with hard, slippery, and soft grounds in a unified manner expressed by two parameters only. By computing trotting and jumping motions for a quadruped robot, the proposed optimization demonstrates the versatility for multi-contact motion planning on surfaces with different physical properties.

Guiyang Xin, Carlo Tiseo, Wouter Wolfslag et al.

The deployment of robots in industrial and civil scenarios is a viable solution to protect operators from danger and hazards. Shared autonomy is paramount to enable remote control of complex systems such as legged robots, allowing the operator to focus on the essential tasks instead of overly detailed execution. To realize this, we propose a comprehensive control framework for inspection and intervention using a legged robot and validate the integration of multiple loco-manipulation algorithms optimised for improving the remote operation. The proposed control offers 3 operation modes: fully automated, semi-autonomous, and the haptic interface receiving onsite physical interaction for assisting teleoperation. Our contribution is the design of a QP-based semi-analytical whole-body control, which is the key to the various task completion subject to internal and external constraints. We demonstrate the versatility of the whole-body control in terms of decoupling tasks, singularity tolerance and constraint satisfaction. We deploy our solution in field trials and evaluate in an emergency setting by an E-stop while the robot is clearing road barriers and traversing difficult terrains.

Eleftherios Triantafyllidis, Christopher McGreavy, Jiacheng Gu et al.

Research in multi-modal interfaces aims to provide solutions to immersion and increase overall human performance. A promising direction is combining auditory, visual and haptic interaction between the user and the simulated environment. However, no extensive comparisons exist to show how combining audiovisuohaptic interfaces affects human perception reflected on task performance. Our paper explores this idea. We present a thorough, full-factorial comparison of how all combinations of audio, visual and haptic interfaces affect performance during manipulation. We evaluate how each interface combination affects performance in a study (N=25) consisting of manipulating tasks of varying difficulty. Performance is assessed using both subjective, assessing cognitive workload and system usability, and objective measurements, incorporating time and spatial accuracy-based metrics. Results show that regardless of task complexity, using stereoscopic-vision with the VRHMD increased performance across all measurements by 40% compared to monocular-vision from the display monitor. Using haptic feedback improved outcomes by 10% and auditory feedback accounted for approximately 5% improvement.

Keyhan Kouhkiloui Babarahmati, Carlo Tiseo, Quentin Rouxel et al.

Robotic teleoperation will allow us to perform complex manipulation tasks in dangerous or remote environments, such as needed for planetary exploration or nuclear decommissioning. This work proposes a novel telemanipulation architecture using a passive Fractal Impedance Controller (FIC), which does not depend upon an active viscous component for stability guarantees. Compared to a traditional impedance controller in ideal conditions (no delays and maximum communication bandwidth), our proposed method yields higher transparency in interaction and demonstrates superior dexterity and capability in our telemanipulation test scenarios. We also validate its performance with extreme delays up to 1 s and communication bandwidths as low as 10 Hz. All results validate a consistent stability when using the proposed controller in challenging conditions, regardless of operator expertise.

Wouter Wolfslag, Christopher McGreavy, Guiyang Xin et al.

Legged robots have great potential to perform loco-manipulation tasks, yet it is challenging to keep the robot balanced while it interacts with the environment. In this paper we study the use of additional contact points for maximising the robustness of loco-manipulation motions. Specifically, body-ground contact is studied for enhancing robustness and manipulation capabilities of quadrupedal robots. We propose to equip the robot with prongs: small legs rigidly attached to the body which ensure body-ground contact occurs in controllable point-contacts. The effect of these prongs on robustness is quantified by computing the Smallest Unrejectable Force (SUF), a measure of robustness related to Feasible Wrench Polytopes. We apply the SUF to assess the robustness of the system, and propose an effective approximation of the SUF that can be computed at near-real-time speed. We design a hierarchical quadratic programming based whole-body controller that controls stable interaction when the prongs are in contact with the ground. This novel concept of using prongs and the resulting control framework are all implemented on hardware to validate the effectiveness of the increased robustness and newly enabled loco-manipulation tasks, such as obstacle clearance and manipulation of a large object.

Zhaole Sun, Kai Yuan, Wenbin Hu et al.

In robotic grasping, objects are often occluded in ungraspable configurations such that no pregrasp pose can be found, eg large flat boxes on the table that can only be grasped from the side. Inspired by humans' bimanual manipulation, eg one hand to lift up things and the other to grasp, we address this type of problems by introducing pregrasp manipulation - push and lift actions. We propose a model-free Deep Reinforcement Learning framework to train control policies that utilize visual information and proprioceptive states of the robot to autonomously discover robust pregrasp manipulation. The robot arm learns to first push the object towards a support surface and establishes a pivot to lift up one side of the object, thus creating a clearance between the object and the table for possible grasping solutions. Furthermore, we show the effectiveness of our proposed learning framework in training robust pregrasp policies that can directly transfer from simulation to real hardware through suitable design of training procedures, state, and action space. Lastly, we evaluate the effectiveness and the generalisation ability of the learned policies in real-world experiments, and demonstrate pregrasp manipulation of objects with various size, shape, weight, and surface friction.

Ruoshi Wen, Kai Yuan, Qiang Wang et al.

Regulating contact forces with high precision is crucial for grasping and manipulating fragile or deformable objects. We aim to utilize the dexterity of human hands to regulate the contact forces for robotic hands and exploit human sensory-motor synergies in a wearable and non-invasive way. We extracted force information from the electric activities of skeletal muscles during their voluntary contractions through surface electromyography (sEMG). We built a regression model based on a Neural Network to predict the gripping force from the preprocessed sEMG signals and achieved high accuracy (R2 = 0.982). Based on the force command predicted from human muscles, we developed a force-guided control framework, where force control was realized via an admittance controller that tracked the predicted gripping force reference to grasp delicate and deformable objects. We demonstrated the effectiveness of the proposed method on a set of representative fragile and deformable objects from daily life, all of which were successfully grasped without any damage or deformation.

Wenbin Hu, Iordanis Chatzinikolaidis, Kai Yuan et al.

This paper studies bipedal locomotion as a nonlinear optimization problem based on continuous and discrete dynamics, by simultaneously optimizing the remaining step duration, the next step duration and the foot location to achieve robustness. The linear inverted pendulum as the motion model captures the center of mass dynamics and its low-dimensionality makes the problem more tractable. We first formulate a holistic approach to search for optimality in the three-dimensional parametric space and use these results as baseline. To further improve computational efficiency, our study investigates a sequential approach with two stages of customized optimization that first optimizes the current step duration, and subsequently the duration and location of the next step. The effectiveness of both approaches is successfully demonstrated in simulation by applying different perturbations. The comparison study shows that these two approaches find mostly the same optimal solutions, but the latter requires considerably less computational time, which suggests that the proposed sequential approach is well suited for real-time implementation with a minor trade-off in optimality.

Doo Re Song, Chuanyu Yang, Christopher McGreavy et al.

This paper presents a deep learning framework that is capable of solving partially observable locomotion tasks based on our novel interpretation of Recurrent Deterministic Policy Gradient (RDPG). We study on bias of sampled error measure and its variance induced by the partial observability of environment and subtrajectory sampling, respectively. Three major improvements are introduced in our RDPG based learning framework: tail-step bootstrap of interpolated temporal difference, initialisation of hidden state using past trajectory scanning, and injection of external experiences learned by other agents. The proposed learning framework was implemented to solve the Bipedal-Walker challenge in OpenAI's gym simulation environment where only partial state information is available. Our simulation study shows that the autonomous behaviors generated by the RDPG agent are highly adaptive to a variety of obstacles and enables the agent to effectively traverse rugged terrains for long distance with higher success rate than leading contenders.

Yiming Yang, Vladimir Ivan, Zhibin Li et al.

In this paper, we propose a novel inverse Dynamic Reachability Map (iDRM) that allows a floating base system to find valid end-poses in complex and dynamically changing environments in real-time. End-pose planning for valid stance pose and collision-free configuration is an essential problem for humanoid applications, such as providing goal states for walking and motion planners. However, this is non-trivial in complex environments, where standing locations and reaching postures are restricted by obstacles. Our proposed iDRM customizes the robot-to-workspace occupation list and uses an online update algorithm to enable efficient reconstruction of the reachability map to guarantee that the selected end-poses are always collision-free. The iDRM was evaluated in a variety of reaching tasks using the 38 degree-of-freedom (DoF) humanoid robot Valkyrie. Our results show that the approach is capable of finding valid end-poses in a fraction of a second. Significantly, we also demonstrate that motion planning algorithms integrating our end-pose planning method are more efficient than those not utilizing this technique.