arXiv subjects

Lokesh Krishna

Publications and source records attributed to Lokesh Krishna.

8 recordsLinked to original sources

arXiv2026

ViBe: Visual Behavior Adaptation for Perceptive Humanoid Whole-Body Control

Motion tracking provides a scalable recipe for humanoid whole-body control. By design, the resulting trackers lack exteroceptive feedback hence reacting to the environment remains the responsibility of a higher-level planner. Existing perceptive controllers train geometry-only encoders from scratch, trading semantics for sim-to-real ease, and typically rely on teacher-student distillation for a task of interest. We present ViBe, a post-training framework for adapting motion trackers to perceptive control tasks. We leverage pre-trained visual encoders with a multi-query extractor module to learn task-relevant perceptive feedback. This feedback is grafted onto the tracker's input via low-rank adapters, enabling parameter-efficient fine-tuning. Given a task reward and a reference dataset, this modular controller can be adapted directly via policy optimization. Across four tasks, ViBe shows zero-shot sim-to-real transfer spanning perceptive walking on curbs and parkour, Repose Cube, omni-object loco-manipulation, and dodgeball, with visually robust performance across outdoor, low-light, and RGB distractor conditions. Finally, we solve a goal-oriented Repose Cube task with a deliberately simple planner, demonstrating the efficacy of perceptive controllers, adapted by our approach.

cs.RO↗

arXiv2025

DiffCoTune: Differentiable Co-Tuning for Cross-domain Robot Control

The deployment of robot controllers is hindered by modeling discrepancies due to necessary simplifications for computational tractability or inaccuracies in data-generating simulators. Such discrepancies typically require ad-hoc tuning to meet the desired performance, thereby ensuring successful transfer to a target domain. We propose a framework for automated, gradient-based tuning to enhance performance in the deployment domain by leveraging differentiable simulators. Our method collects rollouts in an iterative manner to co-tune the simulator and controller parameters, enabling systematic transfer within a few trials in the deployment domain. Specifically, we formulate multi-step objectives for tuning and employ alternating optimization to effectively adapt the controller to the deployment domain. The scalability of our framework is demonstrated by co-tuning model-based and learning-based controllers of arbitrary complexity for tasks ranging from low-dimensional cart-pole stabilization to high-dimensional quadruped and biped tracking, showing performance improvements across different deployment domains.

cs.RO↗

arXiv2024

Preferenced Oracle Guided Multi-mode Policies for Dynamic Bipedal Loco-Manipulation

Dynamic loco-manipulation calls for effective whole-body control and contact-rich interactions with the object and the environment. Existing learning-based control synthesis relies on training low-level skill policies and explicitly switching with a high-level policy or a hand-designed finite state machine, leading to quasi-static behaviors. In contrast, dynamic tasks such as soccer require the robot to run towards the ball, decelerate to an optimal approach to dribble, and eventually kick a goal - a continuum of smooth motion. To this end, we propose Preferenced Oracle Guided Multi-mode Policies (OGMP) to learn a single policy mastering all the required modes and preferred sequence of transitions to solve uni-object loco-manipulation tasks. We design hybrid automatons as oracles to generate references with continuous dynamics and discrete mode jumps to perform a guided policy optimization through bounded exploration. To enforce learning a desired sequence of mode transitions, we present a task-agnostic preference reward that enhances performance. The proposed approach demonstrates successful loco-manipulation for tasks like soccer and moving boxes omnidirectionally through whole-body control. In soccer, a single policy learns to optimally reach the ball, transition to contact-rich dribbling, and execute successful goal kicks and ball stops. Leveraging the oracle's abstraction, we solve each loco-manipulation task on robots with varying morphologies, including HECTOR V1, Berkeley Humanoid, Unitree G1, and H1, using the same reward definition and weights.

cs.RO↗

arXiv2024

OGMP: Oracle Guided Multi-mode Policies for Agile and Versatile Robot Control

The efficacy of reinforcement learning for robot control relies on the tailored integration of task-specific priors and heuristics for effective exploration, which challenges their straightforward application to complex tasks and necessitates a unified approach. In this work, we define a general class for priors called oracles that generate state references when queried in a closed-loop manner during training. By bounding the permissible state around the oracle's ansatz, we propose a task-agnostic oracle-guided policy optimization. To enhance modularity, we introduce task-vital modes, showing that a policy mastering a compact set of modes and transitions can handle infinite-horizon tasks. For instance, to perform parkour on an infinitely long track, the policy must learn to jump, leap, pace, and transition between these modes effectively. We validate this approach in challenging bipedal control tasks: parkour and diving using a 16 DoF dynamic bipedal robot, HECTOR. Our method results in a single policy per task, solving parkour across diverse tracks and omnidirectional diving from varied heights up to 2m in simulation, showcasing versatile agility. We demonstrate successful sim-to-real transfer of parkour, including leaping over gaps up to 105 % of the leg length, jumping over blocks up to 20 % of the robot's nominal height, and pacing at speeds of up to 0.6 m/s, along with effective transitions between these modes in the real robot.

cs.RO↗

arXiv2023

Learning Multimodal Bipedal Locomotion and Implicit Transitions: A Versatile Policy Approach

In this paper, we propose a novel framework for synthesizing a single multimodal control policy capable of generating diverse behaviors (or modes) and emergent inherent transition maneuvers for bipedal locomotion. In our method, we first learn efficient latent encodings for each behavior by training an autoencoder from a dataset of rough reference motions. These latent encodings are used as commands to train a multimodal policy through an adaptive sampling of modes and transitions to ensure consistent performance across different behaviors. We validate the policy performance in simulation for various distinct locomotion modes such as walking, leaping, jumping on a block, standing idle, and all possible combinations of inter-mode transitions. Finally, we integrate a task-based planner to rapidly generate open-loop mode plans for the trained multimodal policy to solve high-level tasks like reaching a goal position on a challenging terrain. Complex parkour-like motions by smoothly combining the discrete locomotion modes were generated in 3 min. to traverse tracks with a gap of width 0.45 m, a plateau of height 0.2 m, and a block of height 0.4 m, which are all significant compared to the dimensions of our mini-biped platform.

cs.RO↗

arXiv2021

Linear Policies are Sufficient to Realize Robust Bipedal Walking on Challenging Terrains

In this work, we demonstrate robust walking in the bipedal robot Digit on uneven terrains by just learning a single linear policy. In particular, we propose a new control pipeline, wherein the high-level trajectory modulator shapes the end-foot ellipsoidal trajectories, and the low-level gait controller regulates the torso and ankle orientation. The foot-trajectory modulator uses a linear policy and the regulator uses a linear PD control law. As opposed to neural network-based policies, the proposed linear policy has only 13 learnable parameters, thereby not only guaranteeing sample efficient learning but also enabling simplicity and interpretability of the policy. This is achieved with no loss of performance on challenging terrains like slopes, stairs and outdoor landscapes. We first demonstrate robust walking in the custom simulation environment, MuJoCo, and then directly transfer to hardware with no modification of the control pipeline. We subject the biped to a series of pushes and terrain height changes, both indoors and outdoors, thereby validating the presented work.

cs.RO↗

arXiv2021

Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopes

In this paper, with a view toward deployment of light-weight control frameworks for bipedal walking robots, we realize end-foot trajectories that are shaped by a single linear feedback policy. We learn this policy via a model-free and a gradient-free learning algorithm, Augmented Random Search (ARS), in the two robot platforms Rabbit and Digit. Our contributions are two-fold: a) By using torso and support plane orientation as inputs, we achieve robust walking on slopes of up to 20 degrees in simulation. b) We demonstrate additional behaviors like walking backwards, stepping-in-place, and recovery from external pushes of up to 120 N. The end result is a robust and a fast feedback control law for bipedal walking on terrains with varying slopes. Towards the end, we also provide preliminary results of hardware transfer to Digit.

cs.RO↗

arXiv2020

Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach

In this paper, with a view toward fast deployment of locomotion gaits in low-cost hardware, we use a linear policy for realizing end-foot trajectories in the quadruped robot, Stoch $2$. In particular, the parameters of the end-foot trajectories are shaped via a linear feedback policy that takes the torso orientation and the terrain slope as inputs. The corresponding desired joint angles are obtained via an inverse kinematics solver and tracked via a PID control law. Augmented Random Search, a model-free and a gradient-free learning algorithm is used to train this linear policy. Simulation results show that the resulting walking is robust to terrain slope variations and external pushes. This methodology is not only computationally light-weight but also uses minimal sensing and actuation capabilities in the robot, thereby justifying the approach.

cs.RO↗