Ye Zhao

Humanoid robots are designed to perform diverse loco-manipulation tasks. However, they face challenges due to their high-dimensional and unstable dynamics, as well as the complex contact-rich nature of the tasks. Model-based optimal control methods offer flexibility to define precise motion but are limited by high computational complexity and accurate contact sensing. On the other hand, reinforcement learning (RL) handles high-dimensional spaces with strong robustness but suffers from inefficient learning, unnatural motion, and sim-to-real gaps. To address these challenges, we introduce Opt2Skill, an end-to-end pipeline that combines model-based trajectory optimization with RL to achieve robust whole-body loco-manipulation. Opt2Skill generates dynamic feasible and contact-consistent reference motions for the Digit humanoid robot using differential dynamic programming (DDP) and trains RL policies to track these optimal trajectories. Our results demonstrate that Opt2Skill outperforms baselines that rely on human demonstrations and inverse kinematics-based references, both in motion tracking and task success rates. Furthermore, we show that incorporating trajectories with torque information improves contact force tracking in contact-involved tasks, such as wiping a table. We have successfully transferred our approach to real-world applications. <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://opt2skill.github.io</uri>

Use of bacteria in removal of heavy metals, including hexavalent chromium Cr(VI), has been proven to be as effective yet more eco-friendly compared to other existing technologies. However, polluted wastewater usually contains high amounts of salts in addition to the heavy metals and may interfere with the bioremediation process. Thus, the ideal bacterial strain for these scenarios must be resistant to the heavy metal and high salt concentration but still capable of removing the target pollutant. The current paper studies the effect of salinity on the growth and chromium reduction capabilities of the magnetotactic bacteria Magnetospirillum gryphiswaldense (MSR-1). MSR-1 was exposed to 20 mM, 50 mM, and 100 mM NaCl concentrations and monitored for 27 hours by measuring its optical density and chromium concentrations at different time periods. The results showed that the presence of NaCl does not greatly affect the growth of MSR-1 even at increased concentrations. On the other hand, the introduction of salt in the culture hampered the chromium reduction capacity of the strain with the addition 100 mM NaCl resulting in a decrease of 43% on the amount of chromium reduced.

We propose a multiplication-free K-state reserved complex maximum-likelihood-sequence-estimation (MLSE) to mitigate asymmetrical filtering impairments in digital-subcarrier-multiplexing transmissions. A required optical-to-noise ratio of 1.63 dB over the conventional real MLSE is obtained after transmitting 90 GBaud DSCM DP-16QAM signal over 14 WSSs without multiplications.

Model predictive control (MPC) has demonstrated effectiveness for humanoid bipedal locomotion; however, its applicability in challenging environments, such as rough and slippery terrain, is limited by the difficulty of modeling terrain interactions. In contrast, reinforcement learning (RL) has achieved notable success in training robust locomotion policies over diverse terrain, yet it lacks guarantees of constraint satisfaction and often requires substantial reward shaping. Recent efforts in combining MPC and RL have shown promise of taking the best of both worlds, but they are primarily restricted to flat terrain or quadrupedal robots. In this work, we propose an RL-augmented MPC framework tailored for bipedal locomotion over rough and slippery terrain. Our method parametrizes three key components of single-rigid-body-dynamics-based MPC: system dynamics, swing leg controller, and gait frequency. We validate our approach through bipedal robot simulations in NVIDIA IsaacLab across various terrains, including stairs, stepping stones, and low-friction surfaces. Experimental results demonstrate that our RL-augmented MPC framework produces significantly more adaptive and robust behaviors compared to baseline MPC and RL.

We propose a multiplication-free K-state reserved complex maximum-likelihood-sequence-estimation (MLSE) to mitigate asymmetrical filtering impairments in digital-subcarrier-multiplexing transmissions. A required optical-to-noise ratio of 1.63dB over the conventional real MLSE is obtained after transmitting 90 GBaud DSCM DP-16QAM signal over 14 WSSs without multiplications.

This chapter considers the problems of verification and synthesis for robotic systems with respect to complex tasks. In particular, a class of problems will be considered in which uncertainties in both system dynamics as well as environmental perturbations result in in high risk of failure. Abstraction-based methods are introduced which allow for computationally tractable high-level task planning with formal guarantees on the probability of task satisfaction. Then, Gaussian process learning techniques are incorporated into the abstraction model to enable learning of the system and environmental uncertainties. Finally, control policy synthesis algorithms are introduced which allow the robot to safely traverse its environment, learning the uncertainties online until the task can be satisfied with sufficient guarantees.

This paper extends the family of gap-based local planners to unknown dynamic environments through generating provably collision-free properties for hierarchical navigation systems. Existing perception-informed local planners that operate in dynamic environments rely on emergent or empirical robustness for collision avoidance as opposed to performing formal analysis of dynamic obstacles. In addition to this, the obstacle tracking that is performed in these existent planners is often achieved with respect to a global inertial frame, subjecting such tracking estimates to transformation errors from odometry drift. The proposed local planner, dynamic gap, shifts the tracking paradigm to modeling how the free space, represented as gaps, evolves over time. Gap crossing and closing conditions are developed to aid in determining the feasibility of passage through gaps, and a breadth of simulation benchmarking is performed against other navigation planners in the literature where the proposed dynamic gap planner achieves the highest success rate out of all planners tested in all environments.

This paper proposes an optimization-based task and motion planning framework, named “Logic Network Flow”, to integrate signal temporal logic (STL) specifications into efficient mixed-binary linear programmings. In this framework, temporal predicates are encoded as polyhedron constraints on each edge of the network flow, instead of as constraints between the nodes as in the traditional Logic Tree formulation. Synthesized with Dynamic Network Flows, Logic Network Flows render a tighter convex relaxation compared to Logic Trees derived from these STL specifications. Our formulation is evaluated on several multi-robot motion planning case studies. Empirical results demonstrate that our formulation outperforms Logic Tree formulation in terms of computation time for several planning problems. As the problem size scales up, our method still discovers better lower and upper bounds by exploring fewer number of nodes during the branch-and-bound process, although this comes at the cost of increased computational load for each node when exploring branches.

The active electromagnetic suspension is characterized by fast response speed, simple structure and high control accuracy, which ensures the good performance and makes it a research hotspot. Tubular linear permanent magnet vernier motor (TLPMVM) can meet the requirements of high thrust density and low thrust ripple of active electromagnetic suspension system. By comparing the performance of TLPMVM with different topologies, this paper finds out the motor structure scheme suitable for active electromagnetic suspension.

Tactile sensing is pivotal for enhancing robot manipulation abilities by providing crucial feedback for localized information. However, existing sensors often lack the necessary resolution and bandwidth required for intricate tasks. To address this gap, we introduce VibTac, a novel multi-modal tactile sensing finger designed to offer high-resolution and high-bandwidth tactile sensing simultaneously. VibTac seamlessly integrates vision-based and vibration-based tactile sensing modes to achieve high-resolution and high-bandwidth tactile sensing respectively, leveraging a streamlined human-inspired design for versatility in tasks. This paper outlines the key design elements of VibTac and its fabrication methods, highlighting the significance of the Elastomer Gel Pad (EGP) in its sensing mechanism. The sensor's multi-modal performance is validated through 3D reconstruction and spectral analysis to discern tactile stimuli effectively. In experimental trials, VibTac demonstrates its efficacy by achieving over 90% accuracy in insertion tasks involving objects emitting distinct sounds, such as ethernet connectors. Leveraging vision-based tactile sensing for object localization and employing a deep learning model for "click" sound classification, VibTac showcases its robustness in real-world scenarios.

Accurate and nondestructive estimation of plant biomass is crucial for optimizing plant productivity, but existing methods are often expensive and require complex experimental setups. To address this challenge, we developed an automated system for estimating plant root and shoot biomass over the plant's lifecycle in hydroponic systems. This system employs a robotic arm and turntable to capture 40 images at equidistant angles around a hydroponically grown lettuce plant. These images are then processed into silhouettes and used in voxel-based volumetric 3D reconstruction to produce detailed 3D models. We utilize a space carving method along with a raytracing-based optical correction technique to create high-accuracy reconstructions. Analysis of these models demonstrates that our system accurately reconstructs the plant root structure and provides precise measurements of root volume, which can be calibrated to indicate biomass.

Direct-immersion liquid-cooled charging cables, which feature high heat dissipation efficiency, have a wide range of application in pile-side electrical connections of high-power mobile charging equipment. However, the power line conductors in the cable may deviate from the center of the liquid-cooled pipes under external forces, since the power line conductors are only fixed by rigid connection components at both ends, during use. This will result in uneven heat distribution on the cross-section of the coolant pipes, leading to local thermal aging of the pipes and thus reducing the service life of the cables. To address this issue, a liquid-cooled pipe model with internal helical-grooved channels was proposed in this paper, which utilizes its geometric structure to induce transverse liquid flow and enhance heat transfer. COMSOL Multiphysics was employed for the simulation calculation. The results showed that the liquid-cooled pipeline with an internal spiral groove can effectively improve the lateral temperature uniformity when the power line is eccentric by improving the fluid motion shape. This achievement provides theoretical support and a technical path for efficient thermal management of high-power charging station cables.

This work proposes QuadPiPS, a perception-informed framework for quadrupedal foothold planning in the perception space. QuadPiPS employs a novel ego-centric local environment representation, known as the legged egocan, that is extended here to capture unique legged affordances through a joint geometric and semantic encoding that supports local motion planning and control for quadrupeds. QuadPiPS takes inspiration from the Augmented Leafs with Experience on Foliations (ALEF) planning framework to partition the foothold planning space into its discrete and continuous subspaces. To facilitate real-world deployment, QuadPiPS broadens the ALEF approach by synthesizing perception-informed, real-time, and kinodynamically-feasible reference trajectories through search and trajectory optimization techniques. To support deliberate and exhaustive searching, QuadPiPS over-segments the egocan floor via superpixels to provide a set of planar regions suitable for candidate footholds. Nonlinear trajectory optimization methods then compute swing trajectories to transition between selected footholds and provide long-horizon whole-body reference motions that are tracked under model predictive control and whole body control. Benchmarking with the ANYmal C quadruped across ten simulation environments and five baselines reveals that QuadPiPS excels in safety-critical settings with limited available footholds. Real-world validation on the Unitree Go2 quadruped equipped with a custom computational suite demonstrates that QuadPiPS enables terrain-aware locomotion on hardware.

This study addresses the challenge of social bipedal navigation in a dynamic, human-crowded environment, a research area largely underexplored in legged robot navigation. We present a zonotope-based framework that couples prediction and motion planning for a bipedal ego-agent to account for bidirectional influence with the surrounding pedestrians. This framework incorporates a Social Zonotope Network (SZN), a neural network that predicts future pedestrian reachable sets and plans future socially acceptable reachable set for the ego-agent. SZN generates the reachable sets as zonotopes for efficient reachability-based planning, collision checking, and online uncertainty parameterization. Locomotion-specific losses are added to the SZN training process to adhere to the dynamic limits of the bipedal robot that are not explicitly present in the human crowds data set. These loss functions enable the SZN to generate locomotion paths that are more dynamically feasible for improved tracking. SZN is integrated with a Model Predictive Controller (SZN-MPC) for footstep planning for our bipedal robot Digit. SZN-MPC solves for collision-free trajectory by optimizing through SZN’s gradients. Our results demonstrate the framework’s effectiveness in producing a socially acceptable path, with consistent locomotion velocity, and optimality. The SZN-MPC framework is validated with extensive simulations and hardware experiments. Note to Practitioners—This paper is motivated by the challenge of navigating bipedal robots through dynamic, human-crowded environments in a socially acceptable manner. Existing methods for social navigation often only address obstacle avoidance and are demonstrated on a robot with simple dynamics. This paper proposes the Social Zonotope Network (SZN), a novel neural network that couples pedestrian future trajectory prediction and robot motion planning to facilitate socially aware navigation for bipedal robots such as Digit, designed by Agility Robotics. The social behaviors are learned from real open-sourced pedestrian data using the SZN, which outputs the future predictions as reachable sets for each agent in the environment. The SZN is then integrated into a trajectory optimization problem that takes into account personal space preferences and bipedal robot capabilities to design trajectories that are both collision-free and socially acceptable. This work also highlights the computational efficiency of the SZN design that makes it suitable for real-time integration with motion planners. The framework is validated through extensive simulations and hardware experiments. From a practical standpoint, this research provides a framework that can be applied to bipedal robots to improve automation in human-populated environments such as hospitals, shopping centers, and airports. The framework’s ability to automatically adapt to surrounding human movement helps minimize disruptions and ensures that the robot’s presence is not a hindrance to the flow of human traffic. Future work will focus on outdoor deployment, which will require onboard perception capabilities to detect surrounding pedestrians.

This paper presents an incremental replanning algorithm, dubbed LTL-D*, for temporal-logic-based task planning in a dynamically changing environment. Unexpected changes in the environment may lead to failures in satisfying a task specification in the form of a Linear Temporal Logic (LTL). In this study, the considered failures are categorized into two classes: (i) the desired LTL specification can be satisfied via replanning, and (ii) the desired LTL specification is infeasible to meet strictly and can only be satisfied in a "relaxed" fashion. To address these failures, the proposed algorithm finds an optimal replanning solution that minimally violates desired task specifications. In particular, our approach leverages the D* Lite algorithm and employs a distance metric within the synthesized automaton to quantify the degree of the task violation and then replan incrementally. This ensures plan optimality and reduces planning time, especially when frequent replanning is required. Our approach is implemented in a robot navigation simulation to demonstrate a significant improvement in the computational efficiency for replanning by two orders of magnitude.

Task and motion planning (TAMP) integrates high-level task planning and low-level motion planning to equip robots with the autonomy to effectively reason over long-horizon, dynamic tasks. Optimization-based TAMP focuses on hybrid optimization approaches that define goal conditions via objective functions and are capable of handling open-ended goals, robotic dynamics, and physical interaction between the robot and the environment. Therefore, optimization-based TAMP is particularly suited to solve highly complex, contact-rich locomotion and manipulation problems. This survey provides a comprehensive review on optimization-based TAMP, covering first, planning domain representations, including action description languages and temporal logic, second, individual solution strategies for components of TAMP, including AI planning and trajectory optimization (TO), and finally, the dynamic interplay between logic-based task planning and model-based TO. A particular focus of this survey is to highlight the algorithm structures to efficiently solve TAMP, especially hierarchical and distributed approaches. In addition, the survey emphasizes the synergy between the classical methods and contemporary learning-based innovations, such as large language models. Furthermore, the future research directions for TAMP is discussed in this survey, highlighting both algorithmic and application-specific challenges.

This paper proposes an optimization-based task and motion planning framework, named "Logic Network Flow", to integrate signal temporal logic (STL) specifications into efficient mixed-binary linear programmings. In this framework, temporal predicates are encoded as polyhedron constraints on each edge of the network flow, instead of as constraints between the nodes as in the traditional Logic Tree formulation. Synthesized with Dynamic Network Flows, Logic Network Flows render a tighter convex relaxation compared to Logic Trees derived from these STL specifications. Our formulation is evaluated on several multi-robot motion planning case studies. Empirical results demonstrate that our formulation outperforms Logic Tree formulation in terms of computation time for several planning problems. As the problem size scales up, our method still discovers better lower and upper bounds by exploring fewer number of nodes during the branch-and-bound process, although this comes at the cost of increased computational load for each node when exploring branches.

Humanoid robots offer significant advantages for search and rescue tasks, thanks to their capability to traverse rough terrains and perform transportation tasks. In this study, we present a task and motion planning framework for search and rescue operations using a heterogeneous robot team composed of humanoids and aerial robots. We propose a terrain-aware Model Predictive Controller (MPC) that incorporates terrain elevation gradients learned using Gaussian processes (GP). This terrain-aware MPC generates safe navigation paths for the bipedal robots to traverse rough terrain while minimizing terrain slopes, and it directs the quadrotors to perform aerial search and mapping tasks. The rescue subjects' locations are estimated by a target belief GP, which is updated online during the map exploration. A high-level planner for task allocation is designed by encoding the navigation tasks using syntactically cosafe Linear Temporal Logic (scLTL), and a consensus-based algorithm is designed for task assignment of individual robots. We evaluate the efficacy of our planning framework in simulation in an uncertain environment with various terrains and random rescue subject placements.

We study the problem of computationally efficient control synthesis for Interval Markov Decision Processes (IMDPs), that is, MDPs with interval uncertainty on the transition probabilities, against tasks specified in linear temporal logic. To address the scalability challenge when synthesizing this control policy in a holistic way, we propose decomposing the monolithic global IMDP into a collection of interconnected local IMDPs. We focus on the problem of robotic motion planning. Specifically, we assume a setting in which the transition probabilities can be learned and their interval uncertainty reduced by observing the dynamics of the system at runtime. This creates an objective of exploration to ensure that the planning task can be completed with sufficient probability of success. We perform decoupled exploration and learning on the local IMDPs and then combine local control policies to guarantee global task satisfaction. In a simulation-based case study, we show that, compared to existing approaches, our proposed decomposition leads to faster learning and satisfaction of the planning task and provides a feasible controller when other methods are infeasible.

This study examines the problem of hopping robot navigation planning to achieve simultaneous goal-directed and environment exploration tasks. We consider a scenario in which the robot has mandatory goal-directed tasks defined using Linear Temporal Logic (LTL) specifications as well as optional exploration tasks represented using a reward function. Additionally, there exists uncertainty in the robot dynamics which results in motion perturbation. We first propose an abstraction of 3D hopping robot dynamics which enables high-level planning and a neural-network-based optimization for low-level control. We then introduce a Multi-task Product IMDP (MT-PIMDP) model of the system and tasks. We propose a unified control policy synthesis algorithm which enables both task-directed goal-reaching behaviors as well as task-agnostic exploration to learn perturbations and reward. We provide a formal proof of the trade-off induced by prioritizing either LTL or RL actions. We demonstrate our methods with simulation case studies in a 2D world navigation environment.

Reliable robotic grasping, especially with deformable objects such as fruits, remains a challenging task due to underactuated contact interactions with a gripper, unknown object dynamics and geometries. In this study, we propose a transformer-based robotic grasping framework for rigid grippers that leverage tactile and visual information for safe object grasping. Specifically, the transformer models learn physical feature embeddings with sensor feedback through performing two predefined explorative actions (pinching and sliding) and predict a grasping outcome through a multilayer perceptron with a given grasping strength. Using these predictions, the gripper predicts a safe grasping strength via inference. Compared with convolutional recurrent networks, the transformer models can capture the long-term dependencies across the image sequences and process spatial–temporal features simultaneously. We first benchmark the transformer models on a public dataset for slip detection. Following that, we show that the transformer models outperform a CNN + LSTM model in terms of grasping accuracy and computational efficiency. We also collect a new fruit grasping dataset and conduct online grasping experiments using the proposed framework for both seen and unseen fruits. In addition, we extend our model to objects with different shapes and demonstrate the effectiveness of our pretrained model trained on our large-scale fruit dataset.

This study focuses on a layered, experience-based, multi-modal contact planning framework for agile quadrupedal locomotion over a constrained rebar environment. To this end, our hierarchical planner incorporates locomotion-specific modules into the high-level contact sequence planner and performs kinodynamically-aware trajectory optimization as the low-level motion planner. Through quantitative analysis of the experience accumulation process and experimental validation of the kinodynamic feasibility of the generated locomotion trajectories, we demonstrate that the planning heuristic of experience offers an effective way of providing candidate footholds for a legged contact planner. Additionally, we introduce a guiding torso path heuristic at the global planning level to enhance the navigation success rate in the presence of environmental obstacles. Our results indicate that the torso-path guided experience accumulation requires significantly fewer offline trials to successfully reach the goal compared to regular experience accumulation. Finally, our planning framework is validated in both dynamics simulations and real hardware implementations on a quadrupedal robot provided by Skymul Inc.

This paper presents an incremental replanning algorithm, dubbed LTL-D*, for temporal-logic-based task planning in a dynamically changing environment. Unexpected changes in the environment may lead to failures in satisfying a task specification in the form of a Linear Temporal Logic (LTL). In this study, the considered failures are categorized into two classes: (i) the desired LTL specification can be satisfied via replanning, and (ii) the desired LTL specification is infeasible to meet strictly and can only be satisfied in a "relaxed" fashion. To address these failures, the proposed algorithm finds an optimal replanning solution that minimally violates desired task specifications. In particular, our approach leverages the D* Lite algorithm and employs a distance metric within the synthesized automaton to quantify the degree of the task violation and then replan incrementally. This ensures plan optimality and reduces planning time, especially when frequent replanning is required. Our approach is implemented in a robot navigation simulation to demonstrate a significant improvement in the computational efficiency for replanning by two orders of magnitude.

This study focuses on a layered, experience-based, multi-modal contact planning framework for agile quadrupedal locomotion over a constrained rebar environment. To this end, our hierarchical planner incorporates locomotion-specific modules into the high-level contact sequence planner and solves kinodynamically-aware trajectory optimization as the low-level motion planner. Through quantitative analysis of the experience accumulation process and experimental validation of the kinodynamic feasibility of the generated locomotion trajectories, we demonstrate that the experience planning heuristic offers an effective way of providing candidate footholds for a legged contact planner. Additionally, we introduce a guiding torso path heuristic at the global planning level to enhance the navigation success rate in the presence of environmental obstacles. Our results indicate that the torso-path guided experience accumulation requires significantly fewer offline trials to successfully reach the goal compared to regular experience accumulation. Finally, our planning framework is validated in both dynamics simulations and real hardware implementations on a quadrupedal robot provided by Skymul Inc.

Social navigation for bipedal robots remains relatively unexplored due to the highly complex, nonlinear dynamics of bipedal locomotion. This study presents a preliminary exploration of social navigation for bipedal robots in a human crowded environment. We propose a social path planner that ensures the locomotion safety of the bipedal robot while navigating under a social norm. The proposed planner leverages a conditional variational autoencoder architecture and learns from human crowd datasets to produce a socially acceptable path plan. Robot-specific locomotion safety is formally enforced by incorporating signal temporal logic specifications during the learning process. We demonstrate the integration of the social path planner with a model predictive controller and a low-level passivity controller to enable comprehensive full-body joint control of Digit in a dynamic simulation.

This study proposes a hierarchically integrated framework for safe task and motion planning (TAMP) of bipedal locomotion in a partially observable environment with dynamic obstacles and uneven terrain. The high-level task planner employs linear temporal logic for a reactive game synthesis between the robot and its environment and provides a formal guarantee on navigation safety and task completion. To address environmental partial observability, a belief abstraction model is designed by partitioning the environment into multiple belief regions and employed at the high-level navigation planner to estimate the dynamic obstacles' location. This additional location information of dynamic obstacles offered by belief abstraction enables less conservative long-horizon navigation actions beyond guaranteeing immediate collision avoidance. Accordingly, a synthesized action planner sends a set of locomotion actions to the middle-level motion planner while incorporating safe locomotion specifications extracted from safety theorems based on a reduced-order model (ROM) of the locomotion process. The motion planner employs the ROM to design safety criteria and a sampling algorithm to generate nonperiodic motion plans that accurately track high-level actions. At the low level, a foot placement controller based on an angular-momentum linear inverted pendulum model is implemented and integrated with an ankle-actuated passivity-based controller for full-body trajectory tracking. To address external perturbations, this study also investigates the safe sequential composition of the keyframe locomotion state and achieves robust transitions against external perturbations through reachability analysis. The overall TAMP framework is validated with extensive simulations and hardware experiments on bipedal walking robots Cassie and Digit designed by Agility Robotics.

The force modulation of robotic manipulators has been extensively studied for several decades. However, it is not yet commonly used in safety-critical applications due to a lack of accurate interaction contact modeling and weak performance guarantees—a large proportion of them concerning the modulation of interaction forces. This study presents a high-level framework for simultaneous trajectory optimization and force control of the interaction between a manipulator and soft environments, which is prone to external disturbances. Sliding friction and normal contact force are taken into account. The dynamics of the soft contact model and the manipulator are simultaneously incorporated in a trajectory optimizer to generate desired motion and force profiles. A constrained optimization framework based on the alternative direction method of multipliers has been employed to efficiently generate real-time optimal control inputs and high-dimensional state trajectories in a model-predictive control fashion. The experimental validation of the model performance is conducted on a soft substrate with known material properties using a Cartesian space force control mode. Results show a comparison of ground truth and real-time model-based contact force and motion tracking for multiple Cartesian motions in the valid range of the friction model. It is shown that a contact-model-based motion planner can compensate for frictional forces and motion disturbances and improve the overall motion and force tracking accuracy. The proposed high-level planner has the potential to facilitate the automation of medical tasks involving the manipulation of compliant, delicate, and deformable tissues.

Safe quadrupedal navigation through unknown environments is a challenging problem. This paper proposes a hierarchical vision-based planning framework (GPF-BG) integrating our previous Global Path Follower (GPF) navigation system and a gap-based local planner using Bézier curves, so called <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$B$</tex> ézier Gap (BG). This BG-based trajectory synthesis can generate smooth trajectories and guarantee safety for point-mass robots. With a gap analysis extension based on non-point, rectangular geometry, safety is guaranteed for an idealized quadrupedal motion model and significantly improved for an actual quadrupedal robot model. Stabilized perception space improves performance under oscillatory internal body motions that impact sensing. Simulation-based and real experiments under different benchmarking configurations test safe navigation performance. GPF-BG has the best safety outcomes across all experiments.

This paper addresses the problem of temporal-logic-based planning for bipedal robots in uncertain environments. We first propose an Interval Markov Decision Process abstraction of bipedal locomotion (IMDP-BL). Motion perturbations from multiple sources of uncertainty are incorporated into our model using stacked Gaussian process learning in order to achieve formal guarantees on the behavior of the system. We consider tasks which can be specified using Linear Temporal Logic (LTL). Through a product IMDP construction combining the IMDP-BL of the bipedal robot and a Deterministic Rabin Automaton (DRA) of the specifications, we synthesize control policies which allow the robot to safely traverse the environment, iteratively learning the unknown dynamics until the specifications can be satisfied with satisfactory probability. We demonstrate our methods with simulation case studies.

The ability of bipedal robots to adapt to diverse and unstructured terrain conditions is crucial for their deployment in real-world environments. To this end, we present a novel, bio-inspired robot foot design with stabilizing tarsal segments and a multifarious sensor suite involving acoustic, capacitive, tactile, temperature, and acceleration sensors. A real-time signal processing and terrain classification system is developed and evaluated. The sensed terrain information is used to control actuated segments of the foot, leading to improved ground contact and stability. The proposed framework highlights the potential of the sensor-integrated adaptive foot for intelligent and adaptive locomotion.