A Behavior-Based Reinforcement Learning Approach to Control Walking Bipedal Robots Under Unknown Disturbances

Beranek, R.; Karimi, Masoud; Ahmadi, Mojtaba

doi:10.1109/tmech.2021.3120628

Cited by 12 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guided by the ZMP formulation, a mobile manipulator's base generates stability-compensating motions, while the manipulator arm is executing tasks [3], [4]. By using potential functions derived from stability measures including the ZMP formulation, stability-compensating motion can also be generated for manipulator arms, as demonstrated in [5]- [10]. However, stability-compensating motions aim to complete a task while optimizing stability, while stabilityconstrained time-optimal motions aim to complete a task within the shortest amount of time without violating the stability constraint.…”

Section: B Related Literaturementioning

confidence: 99%

Chance-Constrained Rollover-Free Manipulation Planning With Uncertain Payload Mass

Song,

Petraki,

DeHart

et al. 2024

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

This paper presents a chance-constrained rollover-free manipulation planning method for robotic arms under payload mass uncertainty. The corresponding motion planning problem is stated as a chance-constrained nonlinear optimal control problem (NOCP) subject to kinematics and rollover stability constraints. The latter takes the form of a chance constraint that ensures a certain probability of the robot maintaining dynamic rollover stability in the presence of payload mass uncertainty. To achieve efficient solutions to the NOCP, a novel geometric bound for the stability region is derived. The novel bound is then utilized to modify the rollover-stability constraint. To showcase its benefit, comparisons between the proposed bound of probabilistic rollover stability measure and the naive noise model are provided through statistical analysis. The formulation's practicality is demonstrated through experiments with a Kinova Jaco 2 arm mounted on a free-to-roll platform. Results demonstrate greater robustness of the robot's motion plan to mass uncertainty and computational efficiency of the trajectory generation. ÂHosted file

show abstract

Section: B Related Literaturementioning

confidence: 99%

Chance-Constrained Rollover-Free Manipulation Planning With Uncertain Payload Mass

Song,

Petraki,

DeHart

et al. 2024

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

show abstract

“…Guided by the ZMP formulation, a mobile manipulator's base generates stability-compensating motions, while the manipulator arm is executing tasks [3], [4]. By using potential functions derived from stability measures including the ZMP formulation, stability-compensating motion can also be generated for manipulator arms, as demonstrated in [5]- [10]. However, requiring a mobile manipulator robot to continuously generate motion that compensates for stability during operations will reduce the robot's efficiency for task completion; ideally, stability compensating motion should only occur when rollover risk is imminent.…”

Section: B Related Literaturementioning

confidence: 99%

Chance-Constrained Rollover-Free Manipulation Planning with Uncertain Payload Mass

Song¹,

Petraki²,

DeHart³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>This paper presents a chance-constrained rollover-free manipulation planning method for robotic arms under payload mass uncertainty. The corresponding motion planning problem is stated as a chance-constrained nonlinear optimal control problem (NOCP) subject to kinematics and rollover stability constraints. The latter takes the form of a chance constraint that ensures a certain probability of the robot maintaining dynamic rollover stability in the presence of payload mass uncertainty. To achieve efficient solutions to the NOCP, a novel geometric bound for the stability region is derived. The novel bound is then utilized to modify the rollover-stability constraint. To showcase its benefit, comparisons between the proposed bound of probabilistic rollover stability measure and the naive noise model are provided through statistical analysis. The formulation's practicality is demonstrated through experiments with a Kinova Jaco 2 arm mounted on a free-to-roll platform. Results demonstrate greater robustness of the robot's motion plan to mass uncertainty and computational efficiency of the trajectory generation. </p>

show abstract

“…Despite recent advancements, certain obstacles remain. These include high computational demands, limitations in intricate environments, dependence on training data quality, and specialized designs that compromise versatility [88], [99], [100]. To address these challenges, proposed solutions involve integrating multiple control strategies like MPC, optimal trajectory planning, and reinforcement learning [101]- [104].…”

Section: Stability and Locomotion In Bipedal Wheel-legged Robotsmentioning

confidence: 99%

Evolution, Design, and Future Trajectories on Bipedal Wheel-legged Robot: A Comprehensive Review

Mansor,

Irawan,

Abas

2023

IJRCS

View full text Add to dashboard Cite

This comprehensive review delves into the realm of bipedal wheel-legged robots, focusing on their design, control, and applications in assistive technology and disaster mitigation. Drawing insights from various fields such as robotics, computer science, and biomechanics, it offers a holistic understanding of these robots' stability, adaptability, and efficiency. The analysis encompasses optimization techniques, sensor integration, machine learning, and adaptive control methods, evaluating their impact on robot capabilities. Emphasizing the need for adaptable, terrain-aware control algorithms, the review explores the untapped potential of machine learning and soft robotics in enhancing performance across diverse operational scenarios. It highlights the advantages of hybrid models combining legged and wheeled mobility while stressing the importance of refining control frameworks, trajectory planning, and human-robot interactions. The concept of integrating soft and compliant mechanisms for improved adaptability and resilience is introduced. Identifying gaps in current research, the review suggests future directions for investigation in the fields of robotics and control engineering, addressing the evolution and terrain adaptability of bipedal wheel-legged robots, control, stability, and locomotion, as well as integrated sensory and perception systems, microcontrollers, cutting-edge technology, and future design and control directions.

show abstract

A Behavior-Based Reinforcement Learning Approach to Control Walking Bipedal Robots Under Unknown Disturbances

Cited by 12 publications

References 36 publications

Chance-Constrained Rollover-Free Manipulation Planning With Uncertain Payload Mass

Chance-Constrained Rollover-Free Manipulation Planning With Uncertain Payload Mass

Chance-Constrained Rollover-Free Manipulation Planning with Uncertain Payload Mass

Evolution, Design, and Future Trajectories on Bipedal Wheel-legged Robot: A Comprehensive Review

Contact Info

Product

Resources

About