A Learning Behaviour Based Controller for Maintaining Balance in Robotic Locomotion
Bibliographic record
Abstract
Maintaining balance in robotic systems has become an increasingly important control task as roboticists move towards designing systems, such as legged robots and mobile manipulators, to operate in unstructured environments.The balance problem is especially challenging for bipedal systems such as humanoid robots and exoskeletons.These systems have a small support polygon and a higher centre of mass (COM), making it more challenging to maintain balance.Although new control strategies have increased the robustness of bipeds to certain disturbances, they still lack the ability to walk on varied, uneven terrains, and to compensate for unknown disturbances.The Behaviour-Based Locomotion Controller (BBLC) proposed in this thesis is a novel controller for robotic locomotion that introduces an architecture capable of generating new balancing strategies to compensate for unknown disturbances in the environment.The core feature of the BBLC is to apply the Behaviour-Based Control (BBC) architecture to the balance problem.In this architecture, several simpler control behaviours are combined together to generate more complex control strategies.In the BBLC, behaviours consist of different methods of planning task-space trajectories such as foot swing motions, torso motions and COM motions, in the case of a bipedal robot.A learning algorithm is then applied to determine which combination of behaviours result in successful balancing strategies for a given disturbance.The BBLC is initially evaluated in simulation on two separate systems, a mobile manipulator and a planar biped.In both cases, the BBLC generates new balancing strategies which maintain balance when an unknown disturbance is applied.The BBLC is then implemented on ABL-BI (Advanced Biomechatronics and Locomotion Laboratory -Biped One), a 13 degree of freedom bipedal robot designed to experimentally evaluate the BBLC.Initial learning of balancing strategies is performed in a 3D dynamic simulation of ABL-BI.The same disturbances were then applied to the experimental platform, where the results show that the learnt strategies from simulation were activated and increased the robustness of the system.Using a linear inverted pendulum model, it is shown the BBLC is capable of identifying a change in the stable region (in the COM phase plane) of the controller and select behaviours which can compensate for this change.These results confirm the BBLC generates new emergent balancing strategies capable of compensating for disturbances which are unknown to the controller.This controller architecture presents a novel framework capable of learning and adapting to a wide variety of disturbances, without needing a priori controller design for each disturbance case. SSRSingle Stance Right ZMP Zero Moment Point xxi
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".